Linkedin    Twitter   Facebook

Get Started
Get a Demo

Linkedin    Twitter

Articles Tagged with: Innovation and Alternative Data

Case Study: Securitization Disclosure File Creation Process

The Client

Private Label Mortgage-Backed Security Issuer 

The Problem

The client issues private label MBS with sources from multiple origination channels. In accordance with industry requirements, the client needed to create and make available to securitization counterparties a loan-level data file (the “ASF File”) which has been defined and endorsed by the Structured Finance Industry Group. ​

The process of extraction and aggregation was inefficient and inconsistent with data from various originators, due diligence vendors and service providers.

RiskSpan consulting services streamlined extraction and aggregation, and reconciling the data used in this process.

The Solution

RiskSpan automated and improved the client’s processes to aggregate loan level data and perform data quality business rules. RiskSpan also designed, built, tested, and delivered an automated process to perform quality control business rules and produce the ASF File, while producing a reconciled file meeting ASF File standards and specifications.

Data Lineage

RiskSpan has experience working with various financial institutions on data lineage and its best practices. RiskSpan has also partnered with industry-leading data lineage solution providers to harness technical solutions for data lineage.

Data Quality

It’s increasingly important to reduce inefficiency in the data process and one of the key criteria to achieve the same is to ensure Data is of highest quality for downstream or any other analytical application usage. Riskspan experience in data quality stems from working with raw loan and transactional data from some of the world’s largest financial institutions.

The Deliverables

  • Created and documented data dictionary, data mapping, business procedures and business flows​
  • Gathered criteria and knowledge, from various client departments, to assess the reasonableness of data used in the securitization process ​
  • Documented client-specific business logic and business rules to reduce resource dependency and increase organizational transparency​
  • Enforced business rules through an automated mechanism, reducing manual effort and data scrub process time​
  • Delivered exception reporting which enabled the client to track, measure and report inaccuracies in data from due diligence firm​
  • Eliminated maintenance and dependency on ad hoc data sources and manual work-arounds​

Blockchain and Structured Finance

Blockchain has the potential to revolutionize the financial services industry, in particular structured finance, and is rapidly becoming more of a when than an if. A main reason for the failure of the private-label residential mortgage-backed securities market to return to pre-crisis levels is due to a failure in trust, but this stalled market is ripe for innovations.

Why Blockchain?

Today’s model for mortgage data exchange is based on an outdated notion of what is technologically feasible. The servicer’s database is still thought of as a stand alone system-of-record and the investor’s database as a downstream applications that needs to rely on, reconcile, and make sense of loan-level ‘tapes generated by the system-of-record.

This model of a single system-of-record housed with the servicer could be transformed into a blockchain, with every detail of every mortgage and all subsequent transactions captured and distributed to investors. With this new model, investor reporting as it exists today would cease to exist.

This new method would instantly update investors with borrow activity, such as refinancing, prepayment, and rejected payments. On a blockchain, these transactions are a sequence that everyone can decipher.

Using Blockchain to Garner Trust in the PLS Market

Information asymmetry is consistently a problem for many in the PLS space, with many transactions having 10 or more parties contributing to verifying and validating data, documents, or cash flows in some way. Blockchain can help to overcome this asymmetry and among other challenges, share loan-level data with investors, re-envision the due diligence process, and modernize document custody, by allowing private blockchains to share information and document access with relevant parties.

The current steps for the due-diligence process are representative of the lack of trust in the PLS market. Increased transparency, using blockchain technology, could help to restore some trust and make the process run with less resistance.  Automation can streamline the due-diligence process, taking out the 100% file review that is currently required, and adding this to a secure blockchain only available to select parties. If reconciliations are deemed necessary for an individual loan file, the results could be automated and added to this blockchain.

Blockchain and Consensus

Talk about implementing blockchain into the realm of structured finance cannot ignore the issue of consensus, something at the heart of all distributed-ledger systems. Private (or ‘permissioned’) blockchains are designed for a specific business purpose, so achieving consensus requires data posted to the blockchain to be verified in an automated way by all parties relevant to the transaction.

Much of blockchain’s appeal is bound up in the promise of an environment in which deal participants can gain reasonable assurance that their counterparts are disclosing information that is both accurate and comprehensive. Visibility is an important component of this, but ultimately, achieving consensus that what is being done is what ought to be done will be necessary in order to fully eliminate redundant functions in business processes and overcome information asymmetry in the private markets. Sophisticated, well-conceived algorithms that enable private parties to arrive at this consensus in real time will be key.


Talk Scope

Applying Machine Learning to Conventional Model Validations

In addition to transforming the way in which financial institutions approach predictive modeling, machine learning techniques are beginning to find their way into how model validators assess conventional, non-machine-learning predictive models. While the array of standard statistical techniques available for validating predictive models remains impressive, the advent of machine learning technology has opened new avenues of possibility for expanding the rigor and depth of insight that can be gained in the course of model validation. In this blog post, we explore how machine learning, in some circumstances, can supplement a model validator’s efforts related to:

  • Outlier detection on model estimation data
  • Clustering of data to better understand model accuracy
  • Feature selection methods to determine the appropriateness of independent variables
  • The use of machine learning algorithms for benchmarking
  • Machine learning techniques for sensitivity analysis and stress testing



Outlier Detection

Conventional model validations include, when practical, an assessment of the dataset from which the model is derived. (This is not always practical—or even possible—when it comes to proprietary, third-party vendor models.) Regardless of a model’s design and purpose, virtually every validation concerns itself with at least a cursory review of where these data are coming from, whether their source is reliable, how they are aggregated, and how they figure into the analysis.

Conventional model validation techniques sometimes overlook (or fail to look deeply enough at) the question of whether the data population used to estimate the model is problematic. Outliers—and the effect they may be having on model estimation—can be difficult to detect using conventional means. Developing descriptive statistics and identifying data points that are one, two, or three standard deviations from the mean (i.e., extreme value analysis) is a straightforward enough exercise, but this does not necessarily tell a modeler (or a model validator) which data points should be excluded.

Machine learning modelers use a variety of proximity and projection methods for filtering outliers from their training data. One proximity method employs the K-means algorithm, which groups data into clusters centered around defined “centroids,” and then identifies data points that do not appear to belong to any particular cluster. Common projection methods include multi-dimensional scaling, which allows analysts to view multi-dimensional relationships among multiple data points in just two or three dimensions. Sophisticated model validators can apply these techniques to identify dataset problems that modelers may have overlooked.


Data Clustering

The tendency of data to cluster presents another opportunity for model validators. Machine learning techniques can be applied to determine the relative compactness of individual clusters and how distinct individual clusters are from one another. Clusters that do not appear well defined and blur into one another are evidence of a potentially problematic dataset—one that may result in non-existent patterns being identified in random data. Such clustering could be the basis of any number of model validation findings.



Feature (Variable) Selection

What conventional predictive modelers typically refer to as variables are commonly referred to by machine learning modelers as features. Features and variables serve essentially the same function, but the way in which they are selected can differ. Conventional modelers tend to select variables using a combination of expert judgment and statistical techniques. Machine learning modelers tend to take a more systematic approach that includes stepwise procedures, criterion-based procedures, lasso and ridge regresssion and dimensionality reduction. These methods are designed to ensure that machine learning models achieve their objectives in the simplest way possible, using the fewest possible number of features, and avoiding redundancy. Because model validators frequently encounter black-box applications, directing applying these techniques is not always possible. In some limited circumstances, however, model validators can add to the robustness of their validations by applying machine learning feature selection methods to determine whether conventionally selected model variables resemble those selected by these more advanced means (and if not, why not).


Benchmarking Applications

Identifying and applying an appropriate benchmarking model can be challenging for model validators. Commercially available alternatives are often difficult to (cost effectively) obtain, and building challenger models from scratch can be time-consuming and problematic—particularly when all they do is replicate what the model in question is doing.

While not always feasible, building a machine learning model using the same data that was used to build a conventionally designed predictive model presents a “gold standard” benchmarking opportunity for assessing the conventionally developed model’s outputs. Where significant differences are noted, model validators can investigate the extent to which differences are driven by data/outlier omission, feature/variable selection, or other factors.


 Sensitivity Analysis and Stress Testing

The sheer quantity of high-dimensional data very large banks need to process in order to develop their stress testing models makes conventional statistical analysis both computationally expensive and problematic. (This is sometimes referred to as the “curse of dimensionality.”) Machine learning feature selection techniques, described above, are frequently useful in determining whether variables selected for stress testing models are justifiable.

Similarly, machine learning techniques can be employed to isolate, in a systematic way, those variables to which any predictive model is most and least sensitive. Model validators can use this information to quickly ascertain whether these sensitivities are appropriate. A validator, for example, may want to take a closer look at a credit model that is revealed to be more sensitive to, say, zip code, than it is to credit score, debt-to-income ratio, loan-to-value ratio, or any other individual variable or combination of variables. Machine learning techniques make it possible for a model validator to assess a model’s relative sensitivity to virtually any combination of features and make appropriate judgments.



Model validators have many tools at their disposal for assessing the conceptual soundness, theory, and reliability of conventionally developed predictive models. Machine learning is not a substitute for these, but its techniques offer a variety of ways of supplementing traditional model validation approaches and can provide validators with additional tools for ensuring that models are adequately supported by the data that underlies them.

Applying Model Validation Principles to Machine Learning Models

Machine learning models pose a unique set of challenges to model validators. While exponential increases in the availability of data, computational power, and algorithmic sophistication in recent years has enabled banks and other firms to increasingly derive actionable insights from machine learning methods, the significant complexity of these systems introduces new dimensions of risk.

When appropriately implemented, machine learning models greatly improve the accuracy of predictions that are vital to the risk management decisions financial institutions make. The price of this accuracy, however, is complexity and, at times, a lack of transparency. Consequently, machine learning models must be particularly well maintained and their assumptions thoroughly understood and vetted in order to prevent wildly inaccurate predictions. While maintenance remains primarily the responsibility of the model owner and the first line of defense, second-line model validators increasingly must be able to understand machine learning principles well enough to devise effective challenge that includes:

  • Analysis of model estimation data to determine the suitability of the machine learning algorithm
  • Assessment of space and time complexity constraints that inform model training time and scalability
  • Review of model training/testing procedure
  • Determination of whether model hyperparameters are appropriate
  • Calculation of metrics for determining model accuracy and robustness

More than one way exists of organizing these considerations along the three pillars of model validation. Here is how we have come to think about it.


Conceptual Soundness

Many of the concepts of reviewing model theory that govern conventional model validations apply equally well to machine learning models. The question of “business fit” and whether the variables the model lands on are reasonable is just as valid when the variables are selected by a machine as it is when they are selected by a human analyst. Assessing the variable selection process “qualitatively” (does it make sense?) as well as quantitatively (measuring goodness of fit by calculating residual errors, among other tests) takes on particular importance when it comes to machine learning models.

Machine learning does not relieve validators of their responsibility assess the statistical soundness of a model’s data. Machine learning models are not immune to data issues. Validators protect against these by running routine distribution, collinearity, and related tests on model datasets. They must also ensure that the population has been appropriately and reasonably divided into training and holdout/test datasets.

Supplementing these statistical tests should be a thorough assessment of the modeler’s data preparation procedures. In addition to evaluating the ETL process—a common component of all model validations—effective validations of machine learning models take particular notice of variable “scaling” methods. Scaling is important to machine learning algorithms because they generally do not take units into account. Consequently, a machine learning model that relies on borrower income (generally ranging between tens of thousands and hundreds of thousands of dollars), borrower credit score (which generally falls within a range of a few hundred points) and loan-to-value ratio (expressed as a percentage), needs to apply scaling factors to normalize these ranges in order for the model to correctly process each variable’s relative importance. Validators should ensure that scaling and normalizations are reasonable.

Model assumptions, when it comes to machine learning validation, are most frequently addressed by looking at the selection, optimization, and tuning of the model’s hyperparameters. Validators must determine whether the selection/identification process undertaken by the modeler (be it grid search, random search, Bayesian Optimization, or another method—see this blog post for a concise summary of these) is conceptually sound.


Process Verification

Machine learning models are no more immune to overfitting and underfitting (the bias-variance dilemma) than are conventionally developed predictive models. An overfitted model may perform well on the in-sample data, but predict poorly on the out-of-sample data. Complex nonparametric and nonlinear methods used in machine learning algorithms combined with high computing power are likely to contribute to an overfitted machine learning model. An underfitted model, on the other hand, performs poorly in general, mainly due to an overly simplified model algorithm that does a poor job at interpreting the information contained within data.

Cross-validation is a popular technique for detecting and preventing the fitting or “generalization capability” issues in machine learning. In K-Fold cross-validation, the training data is partitioned into K subsets. The model is trained on all training data except the Kth subset, and the Kth subset is used to validate the performance. The model’s generalization capability is low if the accuracy ratios are consistently low (underfitted) or higher on the training set but lower on the validation set (overfitted). Conventional models, such as regression analysis, can be used to benchmark performance.


Outcomes Analysis

Outcomes analysis enables validators to verify the appropriateness of the model’s performance measure methods. Performance measures (or “scoring methods”) are typically specialized to the algorithm type, such as classification and clustering. Validators can try different scoring methods to test and understand the model’s performance. Sensitivity analyses can be performed on the algorithms, hyperparameters, and seed parameters. Since there is no right or wrong answer, validators should focus on the dispersion of the sensitivity results.


Many statistical tactics commonly used to validate conventional models apply equally well to machine learning models. One notable omission is the ability to precisely replicate the model’s outputs. Unlike with an OLS or ARIMA model, for which a validator can reasonably expect to be able to match the model’s coefficients exactly if given the same data, machine learning models can be tested only indirectly—by testing the conceptual soundness of the selected features and assumptions (hyperparameters) and by evaluating the process and outputs. Applying model validation tactics specially tailored to machine learning models allows financial institutions to deploy these powerful tools with greater confidence by demonstrating that they are of sound conceptual design and perform as expected.

Machine Learning Detects Model Validation Blind Spots

Machine learning represents the next frontier in model validation—particularly in the credit and prepayment modeling arena. Financial institutions employ numerous models to make predictions relating to MBS performance. Validating these models by assessing their predictions is of paramount importance, but even models that appear to perform well based upon summary statistics can have subsets of input (input subspaces) for which they tend to perform poorly. Isolating these “blind spots” can be challenging using conventional model validation techniques, but recently developed machine learning algorithms are making the job easier and the results more reliable. 

High-Error Subspace Visualization

RiskSpan’s modeling team has developed a statistical algorithm which identifies high-error subspaces and flags model outputs corresponding to inputs originating from these subspaces, indicating to model users that the results might be unreliable. An extension to this problem that we also address is whether migration of data points to more error-prone subspaces of the input space over time can be indicative of macroeconomic regime shifts and signal a need to re-estimate the model. This will aid in the prevention of declining model efficacy over time.

Due to the high-dimensional nature of the input spaces of many financial models, traditional statistical methods of partitioning data may prove inadequate. Using machine learning techniques, we have developed a more robust method of high-error subspace identification. We develop the algorithm using loan performance model data, but the method is adaptable to generic models.

Data Selection and Preparation

The dataset we use for our analysis is a random sample of the publicly available Freddie Mac Loan-Level Dataset. The entire dataset covers the monthly loan performance for loans originated from 1999 to 2016 (25.4 million fixed-rate mortgages). From this set, one million loans were randomly sampled. Features of this dataset include loan-to-value ratio, borrower debt-to-income ratio, borrower credit score, interest rate, and loan status, among others. We aggregate the monthly status vectors for each loan into a single vector which contains a loan status time series over the life of the loan within the historical period. This aggregated status vector is mapped to a value of 1 if the time series indicates the loan was ever 90 days delinquent within the first three years after its origination, representing a default, and 0 otherwise. This procedure results in 914,802 total records.

Algorithm Framework

Using the prepared loan dataset, we estimate a logistic regression loan performance model. The data is sampled and partitioned into training and test datasets for clustering analysis. The model estimation and training data is taken from loans originating in the period from 1999 to 2007, while loans originating in the period from 2008 to 2016 are used for testing. Once the data has been partitioned into training and test sets, a clustering algorithm is run on the training data.

Two-Dimensional Visualization of Select Clusters

The clustering is evaluated based upon its ability to stratify the loan data into clusters that meaningfully identify regions of the input for which the model performs poorly. This requires the average model performance error associated with certain clusters to be substantially higher than the mean. After the training data is assigned to clusters, cluster-level error is computed for each cluster using the logistic regression model. Clusters with high error are flagged based upon a scoring scheme. Each loan in the test set is assigned to a cluster based upon its proximity to the training cluster centers. Loans in the test set that are assigned to flagged clusters are flagged, indicating that the loan comes from a region for which loan performance model predictions exhibit lower accuracy.

Algorithm Performance Analysis

The clustering algorithm successfully flagged high-error regions of the input space, with flagged test clusters exhibiting accuracy more than one standard deviation below the mean. The high errors associated with clusters flagged during model training were persistent over time, with flagged clusters in the test set having a model accuracy of just 38.7%, compared to an accuracy of 92.1% for unflagged clusters. Failure to address observed high-error clusters in the training set and migration of data to high-error subspaces led to substantially diminished model accuracy, with overall model accuracy dropping from 93.9% in the earlier period to 84.1% in the later period.

Training/Test Cluster Error Comparison

Additionally, the nature of default misclassifications and variables with greatest impact on misclassification were also determined. Cluster FICO scores proved to be a strong indicator of cluster model prediction accuracy. While a relatively large proportion of loans in low-FICO clusters defaulted, the logistic regression model substantially overpredicted the number of defaults for these clusters, leading to a large number of Type I errors (inaccurate default predictions) for these clusters. Type II (inaccurate non-default predictions) errors constituted a smaller proportion of overall model error, and their impact was diminished even further when considering their magnitude relative to the number of true negative predictions (accurate non-default predictions), which are far fewer in number than true positive predictions (accurate default predictions).

FICO vs. Cluster Accuracy


Our application of the subspace error identification algorithm to a loan performance model illustrates the dangers of using high-level summary statistics as the sole determinant of model efficacy and failure to consistently monitor the statistical profile of model input data over time. Often, more advanced statistical analysis is required to comprehensively understand model performance. The algorithm identified sets of loans for which the model was systematically misclassifying default status. These large-scale errors come at a high cost to financial institutions employing such models.

As an extension to this research into high error subspace detection, RiskSpan is currently developing machine learning analytics tools that can detect the root cause of systematic model errors and suggest ways to enhance predictive model performance by alleviating these errors.

Permissioned Blockchains–A Quest for Consensus


Conspicuously absent from all the chatter around blockchain’s potential place in structured finance has been much discussion around the thorny matter of consensus. Consensus is at the heart of all distributed ledger networks and is what enables them to function without a trusted central authority. Consensus algorithms are designed to prevent fraud and error. With large, public blockchains, achieving consensus—ensuring that all new information has been examined before is universally accepted—is relatively straightforward. It is achieved either by performing large amounts of work or simply by members who collectively hold a majority stake in the blockchain.

However, when it comes to private (or “permissioned”) blockchains with a relatively small number of interested parties—the kind of blockchains that are currently poised for adoption in the structured finance space—the question of how to obtain consensus takes on an added layer of complexity. Restricting membership greatly reduces the need for elaborate algorithms to prevent fraud on permissioned blockchains. Instead, these applications must ensure that complex workflows and transactions are implemented correctly. They must provide a framework for having members agree to the very structure of the transaction itself. Consensus algorithms complement this by ensuring that the steps performed in verifying transaction data is agreed upon and verified.

With widespread adoption of blockchain in structured finance appearing more and more to be a question of when rather than if, SmartLink Labs, a RiskSpan fintech affiliate, recently embarked on a proof of concept designed to identify and measure the impact of the technology across the structured finance life cycle. The project took a holistic approach, looking at everything from deal issuance to bondholder payments. We sought to understand the benefits, how various roles would change, and the extent to which certain functions might be eliminated altogether. At the heart of virtually every lesson we learned along the way was a common, overriding principle: consensus is hard.

Why is Consensus Hard?

Much of blockchain’s appeal to those of us in the structured finance arena has to do with its potential to lend visibility and transparency to complicated payment rules that govern deals along with dynamic borrower- and collateral-level details that evolve over the lives of the underlying loans. Distributed ledgers facilitate the real-time sharing of these details across all relevant parties—including loan originators, asset servicers, and bond administrators—from deal issuance through the final payment on the transaction. The ledger transactions are synchronized to ensure that ledgers only update when the appropriate participants approve transactions. This is the essence of consensus, and it seems like it ought to be straightforward.

Imagine our surprise when one of the most significant challenges our test implementation encountered was designing the consensus algorithm. Unlike with public blockchains, consensus in a private, or “permissioned,” blockchain is designed for a specific business purpose where the counterparties are known. However, to achieve consensus, the data posted to the blockchain must be verified in an automated manner by the relevant parties to the transaction. One of the challenges with the data and rules that govern most structured transactions is that it is (at best) only partially digital. We approached our project with the premise that most business terms can be translated into a series of logical statements in the form of computer code. Translating unstructured data into structured data in a fully transparent way is problematic, however, and limitations to transparency represent a significant barrier to achieving consensus. In order for a distributed ledger to work in this context, all transaction parties need to reach consensus around how the cash will flow and numerous other business rules throughout the process.


A Potential Solution for Structured Finance

To this end, our initial prototype seeks to test our consensus algorithm on the deal waterfall model. If the industry can move to a process where consensus of the deal waterfall model is achieved at deal issuance, the model posted to the blockchain can then serve as an agreed-upon source of truth and perpetuate through the life of the security—from loan administration to master servicer aggregation and bondholder payments. This business function alone could save the industry countless hours and effectively eliminate all of today’s costs associated with having to model and remodel each transaction multiple times.

Those of us who have been in the structured finance business for 25 years or more know how little the fundamental business processes have evolved. They remain manual, governed largely by paper documents, and prone to human error.

The mortgage industry has proven to be particularly problematic. Little to no transparency in the process has fostered a culture of information asymmetry and general mistrust which has predictably given rise to the need to have multiple unrelated parties double-checking data, performing due diligence reviews on virtually all loan files, validating and re-validating cash flow models, and requiring costly layers of legal payment verification. Ten or more parties might contribute in one way or another to verifying and validating data, documents, or cash flow models for a single deal. Upfront consensus via blockchain holds the potential to dramatically reduce or even eliminate almost all of this redundancy.

Transparency and Real-Time Investor Reporting

The issuance process, of course, is only the beginning. The need for consensus does not end when the cash flow model is agreed to and the deal is finalized. Once we complete a verified deal, the focus of our proof of concept will shift to the monthly process of investor reporting and corresponding payments to the bond holders.

The immutability of transactions posted to the ledger is particularly valuable because of the unmistakable audit trail it creates. Rather than compelling master servicers to rely on a monthly servicing snapshot “tape” to try and figure out what happened to a severely delinquent loan with four instances of non-sufficient funds, a partial payment in suspense, and an interest rate change somewhere in the middle. Putting all these transactions on a blockchain creates a relatively straightforward sequence of transactions that everyone can decipher.

Posting borrower payments to a blockchain in real time will also require consensus among transaction parties. Once this is achieved, the antiquated notion of monthly investor reporting will become obsolete. The potential ramifications of this extend to timing of payments to bond holders. No longer needing to wait until the next month to find out what borrowers did the month before means that payments to investors might be accelerated and, in the private-label security markets, perhaps even more often than monthly. With real-time consensus comes the possibility of far more flexibility for issuers and investors in designing the timing of cash flows should they elect to pursue it.

This envisioned future state is not without its detractors. Some ask why servicers would opt for more transparency when they already encounter more scrutiny and criticism than they would like. In many cases, however, it is the lack of transparency, more than a servicer’s actions themselves, that invite the unwanted scrutiny. Servicers that move beyond reporting monthly snapshots and post comprehensive loan activity to a blockchain stand to reap significant competitive advantages. Because of the real-time consensus and sharing of dynamic loan reporting data (and perhaps of accelerated bond payments, as suggested above) investors will quickly gravitate toward deals that are administered by blockchain-enabled servicers. Sooner or later, servicers who fail to adapt will find themselves on the outside looking in.

Less Redundancy; More Trust

Much of blockchain’s appeal is bound up in the promise of an environment in which deal participants can gain reasonable assurance that their counterparts are disclosing information that is both accurate and comprehensive. Visibility is an important component of this, but ultimately, achieving consensus that what is being done is what ought to be done will be necessary in order to fully eliminate redundant functions in business processes and overcome information asymmetry in the private markets.  Sophisticated, well-conceived algorithms that enable private parties to arrive at this consensus in real time will be key.

One of the enduring lessons of our structured finance proof of concept is that consensus is necessary throughout a transaction’s life. The market (i.e., issuers, investors, servicers, and bond administrators) will ultimately determine what gets posted to a blockchain and what remains off-chain, and more than one business model will likely evolve. As data becomes more structured and more reliable, however, competitive advantages will increasingly accrue to those who adopt consensus algorithms capable of infusing trust into the process. The failure of the private-label MBS market to regain its pre-crisis footing is, in large measure, a failure of trust. Nothing repairs trust like consensus.

Talk Scope

Hands-On Machine Learning–Predicting Loan Delinquency

The ability of machine learning models to predict loan performance makes them particularly interesting to lenders and fixed-income investors. This expanded post provides an example of applying the machine learning process to a loan-level dataset in order to predict delinquency. The process includes variable selection, model selection, model evaluation, and model tuning.

The data used in this example are from the first quarter of 2005 and come from the publicly available Fannie Mae performance dataset. The data are segmented into two different sets: acquisition and performance. The acquisition dataset contains 217,000 loans (rows) and 25 variables (columns) collected at origination (Q1 2005). The performance dataset contains the same set of 217,000 loans coupled with 31 variables that are updated each month over the life of the loan. Because there are multiple records for each loan, the performance dataset contains approximately 16 million rows.

For this exercise, the problem is to build a model capable of predicting which loans will become severely delinquent, defined as falling behind six or more months on payments. This delinquency variable was calculated from the performance dataset for all loans and merged with the acquisition data based on the loan’s unique identifier. This brings the total number of variables to 26. Plenty of other hypotheses can be tested, but this analysis focuses on just this one.

1          Variable Selection

An overview of the dataset can be found below, showing the name of each variable as well as the number of observations available

LOAN_IDENTIFIER                             217088
CHANNEL                                     217088
SELLER_NAME                                 217088
ORIGINAL_INTEREST_RATE                      217088
ORIGINAL_LOAN_TERM                          217088
ORIGINATION_DATE                            217088
FIRST_PAYMENT_DATE                          217088
ORIGINAL_LOAN-TO-VALUE_(LTV)                217088
NUMBER_OF_BORROWERS                         217082
DEBT-TO-INCOME_RATIO_(DTI)                  201580
BORROWER_CREDIT_SCORE                       215114
LOAN_PURPOSE                                217088
PROPERTY_TYPE                               217088
NUMBER_OF_UNITS                             217088
OCCUPANCY_STATUS                            217088
PROPERTY_STATE                              217088
ZIP_(3-DIGIT)                               217088
PRODUCT_TYPE                                217088
CO-BORROWER_CREDIT_SCORE                    100734
MORTGAGE_INSURANCE_TYPE                      34432

Most of the variables in the dataset are fully populated, with the exception of DTI, MI Percentage, MI Type, and Co-Borrower Credit Score. Many options exist for dealing with missing variables, including dropping the rows that are missing, eliminating the variable, substituting with a value such as 0 or the mean, or using a model to fill the most likely value.

The following chart plots the frequency of the 34,000 MI Percentage values.

The distribution suggests a decent amount of variability. Most loans that have mortgage insurance are covered at 25%, but there are sizeable populations both above and below. Mortgage insurance is not required for the majority of borrowers, so it makes sense that this value would be missing for most loans.  In this context, it makes the most sense to substitute the missing values with 0, since 0% mortgage insurance is an accurate representation of the state of the loan. An alternative that could be considered is to turn the variable into a binary yes/no variable indicating if the loan has mortgage insurance, though this would result in a loss of information.

The next variable with a large number of missing values is Mortgage Insurance Type. Querying the dataset reveals that that of the 34,400 loans that have mortgage insurance, 33,000 have type 1 borrower paid insurance and the remaining 1,400 have type 2 lender paid insurance. Like the mortgage insurance variable, the blank values can be filled. This will change the variable to indicate if the loan has no insurance, type 1, or type 2.

The remaining variable with a significant number of missing values is Co-Borrower Credit Score, with approximately half of its values missing. Unlike MI Percentage, the context does not allow us to substitute missing values with zeroes. The distribution of both borrower and co-borrower credit score as well as their relationship can be found below.

As the plot demonstrates, borrower and co-borrower credit scores are correlated. Because of this, the removal of co-borrower credit score would only result in a minimal loss of information (especially within the context of this example). Most of the variance captured by co-borrower credit score is also captured in borrower credit score. Turning the co-borrower credit score into a binary yes/no ‘has co-borrower’ variable would not be of much use in this scenario as it would not differ significantly from the Number of Borrowers variable. Alternate strategies such as averaging borrower/co-borrower credit score might work, but for this example we will simply drop the variable.

In summary, the dataset is now smaller—Co-Borrower Credit Score has been dropped. Additionally, missing values for MI Percentage and MI Type have been filled in. Now that the data have been cleaned up, the values and distributions of the remaining variables can be examined to determine what additional preprocessing steps are required before model building. Scatter matrices of pairs of variables and distribution plots of individual variables along the diagonal can be found below. The scatter plots are helpful for identifying multicollinearity between pairs of variables, and the distributions can show if a variable lacks enough variance that it won’t contribute to model performance.[/vc_column_text][/vc_column][/vc_row][vc_row][vc_column][vc_single_image image=”1089″][/vc_column][/vc_row][vc_row][vc_column][vc_column_text]The third row of scatterplots, above, reflects a lack of variability in the distribution of Original Loan Term. The variance of 3.01 (calculated separately) is very small, and as a result the variable can be removed—it will not contribute to any model as there is very little information to learn from. This process of inspecting scatterplots and distributions is repeated for the remaining pairs of variables. The Number of Units variable suffers from the same issue and can also be removed.

2          Heatmaps and Pairwise Grids

Matrices of scatterplots are useful for looking at the relationships between variables. Another useful plot is a heatmap and pairwise grid of correlation coefficients. In the plot below a very strong correlation between Original LTV and Original CLTV is identified.

This multicollinearity can be problematic for both the interpretation of the relationship between the variables and delinquency as well as the actual performance of some models.  To combat this problem, we remove Original CLTV because Original LTV is a more accurate representation of the loan at origination. Loans in this population that were not refinanced kept their original LTV value as CLTV. If CLTV were included in the model it would introduce information not available at origination to the model. The problem of allowing unexpected additional information in a dataset introduces an issue known as leakage, which will bias the model.

Now that the numeric variables have been inspected, the remaining categorical variables must be analyzed to ensure that the classes are not significantly unbalanced. Count plots and simple descriptive statistics can be used to identify categorical variables are problematic. Two examples below show the count of loans by state and by seller.

Inspecting the remaining variables uncovers that Relocation Indicator (indicating a mortgage issued when an employer moves an employee) and Product Type (fixed vs. adjustable rate) must be removed as they are extremely unbalanced and do not contain any information that will help the models learn. We also removed first payment date and origination date, which were largely redundant. The final cleanup results in a dataset that contains the following columns:


The final two steps before model building are to standardize each of the numeric variables and turn each categorical variable into a series of dummy or indicator variables. Numeric variables are scaled with mean 0 and standard deviation 1 so that it is easier to compare variables that have a different scale (e.g. interest rate vs. LTV). Additionally, standardizing is also a requirement for many algorithms (e.g. principal component analysis).

Categorical variables are transformed by turning each value of the variable into its own yes/no feature. For example, Property State originally has 50 possible values, so it will be turned into 50 variables (e.g. Alabama yes/no, Alaska yes/no).  For categorical variables with many values this transformation will significantly increase the number of variables in the model.

After scaling and transforming the dataset, the final shape is 199,716 rows and 106 columns. The target variable—loan delinquency—has 186,094 ‘no’ values and 13,622 ‘yes’ values. The data are now ready to be used to build, evaluate, and tune machine learning models.

3          Model Selection

Because the target variable loan delinquency is binary (yes/no) the methods available will be classification machine learning models. There are many classification models, including but not limited to: neural networks, logistic regression, support vector machines, decision trees and nearest neighbors. It is always beneficial to seek out domain expertise when tackling a problem to learn best practices and reduce the number of model builds. For this example, two approaches will be tried—nearest neighbors and decision tree.

The first step is to split the dataset into two segments: training and testing. For this example, 40% of the data will be partitioned into the test set, and 60% will remain as the training set. The resulting segmentations are as follows:

1.       60% of the observations (as training set)- X_train

2.       The associated target (loan delinquency) for each observation in X_train- y_train

3.       40% of the observations (as test set)- X_test

4.        The targets associated with the test set- y_test

Data should be randomly shuffled before they are split, as datasets are often in some type of meaningful order. Once the data are segmented the model will first be exposed to the training data to begin learning.

4          K-Nearest Neighbors Classifier

Training a K-neighbors model requires the fitting of the model on X_train (variables) and y_train (target) training observations. Once the model is fit, a summary of the model hyperparameters is returned. Hyperparameters are model parameters not learned automatically but rather are selected by the model creator.


The K-neighbors algorithm searches for the closest (i.e., most similar) training examples for each test observation using a metric that calculates the distance between observations in high-dimensional space.  Once the nearest neighbors are identified, a predicted class label is generated as the class that is most prevalent in the neighbors. The biggest challenge with a K-neighbors classifier is choosing the number of neighbors to use. Another significant consideration is the type of distance metric to use.

To see more clearly how this method works, the 6 nearest neighbors of two random observations from the training set were selected, one that is a non-default (0 label) observation and one that is not.

Random delinquent observation: 28919 
Random non delinquent observation: 59504

The indices and minkowski distances to the 6 nearest neighbors of the two random observations are found below. Unsurprisingly, the first nearest neighbor is always itself and the first distance is 0.

Indices of closest neighbors of obs. 28919 [28919 112677 88645 103919 27218 15512]
Distance of 5 closest neighbor for obs. 28919 [0 0.703 0.842 0.883 0.973 1.011]

Indices of 5 closest neighbors for obs. 59504 [59504 87483 25903 22212 96220 118043]
Distance of 5 closest neighbor for obs. 59504 [0 0.873 1.185 1.186 1.464 1.488]

Recall that in order to make a classification prediction, the kneighbors algorithm finds the nearest neighbors of each observation. Each neighbor is given a ‘vote’ via their class label, and the majority vote wins. Below are the labels (or votes) of either 0 (non-delinquent) or 1 (delinquent) for the 6 nearest neighbors of the random observations. Based on the voting below, the delinquent observation would be classified correctly as 3 of the 5 nearest neighbors (excluding itself) are also delinquent. The non-delinquent observation would also be classified correctly, with 4 of 5 neighbors voting non-delinquent.

Delinquency label of nearest neighbors- non delinquent observation: [0 1 0 0 0 0]
Delinquency label of nearest neighbors- delinquent observation: [1 0 1 1 0 1]


5          Tree-Based Classifier

Tree based classifiers learn by segmenting the variable space into a number of distinct regions or nodes. This is accomplished via a process called recursive binary splitting. During this process observations are continuously split into two groups by selecting the variable and cutoff value that results in the highest node purity where purity is defined as the measure of variance across the two classes. The two most popular purity metrics are the gini index and cross entropy. A low value for these metrics indicates that the resulting node is pure and contains predominantly observations from the same class. Just like the nearest neighbor classifier, the decision tree classifier makes classification decisions by ‘votes’ from observations within each final node (known as the leaf node).

To illustrate how this works, a decision tree was created with the number of splitting rules (max depth) limited to 5. An excerpt of this tree can be found below. All 120,000 training examples start together in the top box. From top to bottom, each box shows the variable and splitting rule applied to the observations, the value of the gini metric, the number of observations the rule was applied to, and the current segmentation of the target variable. The first box indicates that the 6th variable (represented by the 5th index ‘X[5]’) Borrower Credit Score was  used to  split  the  training  examples.  Observations where the value of Borrower Credit Score was below or equal to -0.4413 follow the line to the box on the left. This box shows that 40,262 samples met the criteria. This box also holds the next splitting rule, also applied to the Borrower Credit Score variable. This process continues with X[2] (Original LTV) and so on until the tree is finished growing to its depth of 5. The final segments at the bottom of the tree are the aforementioned leaf nodes which are used to make classification decisions.  When making a prediction on new observations, the same splitting rules are applied and the observation receives the label of the most commonly occurring class in its leaf node.

[/vc_column_text][/vc_column][/vc_row][vc_row][vc_column][vc_single_image image=”1086″][/vc_column][/vc_row][vc_row][vc_column][vc_column_text]A more advanced tree based classifier is the Random Forest Classifier. The Random Forest works by generating many individual trees, often hundreds or thousands. However, for each tree, number of variables considered at each split is limited to a random subset. This helps reduce model variance and de-correlate the trees (since each tree will have a different set of available splitting choices). In our example, we fit a random forest classifier on the training data. The resulting hyperparameters and model documentation indicate that by default the model generates 10 trees, considers a random subset of variables the size of the square root of all variables (approximately 10 in this case), has no depth limitation, and only requires each leaf node to have 1 observation.

Since the random forest contains many trees and does not have a depth limitation, it is incredibly difficult to visualize. In order to better understand the model, a plot showing which variables were selected and resulted in the largest drop in the purity metric (gini index) can be useful. Below are the top 10 most important variables in the model, ranked by the total (normalized) reduction to the gini index.  Intuitively, this plot can be described as showing which variables can be used to best segment the observations into groups that are predominantly one class, either delinquent and non-delinquent.


6          Model Evaluation

Now that the models have been fitted, their performance must be evaluated. To do this, the fitted model will first be used to generate predictions on the test set (X_test). Next, the predicted class labels are compared to the actual observed class label (y_test). Three of the most popular classification metrics that can be used to compare the predicted and actual values are recall, precision, and the f1-score. These metrics are calculated for each class, delinquent and not-delinquent.

Recall is calculated for each class as the ratio of events that were correctly predicted. More precisely, it is defined as the number of true positive predictions divided by the number of true positive predictions plus false negative predictions. For example, if the data had 10 delinquent observations and 7 were correctly predicted, recall for delinquent observations would be 7/10 or 70%.

Precision is the number of true positives divided by the number of true positives plus false positives. Precision can be thought of as the ratio of events correctly predicted to the total number of events predicted. In the hypothetical example above, assume that the model made a total of 14 predictions for the label delinquent. If so, then the precision for delinquent predictions would be 7/14 or 50%.

The f1 score is calculated as the harmonic mean of recall and precision: (2(Precision*Recall/Precision+Recall)).

The classification reports for the K-neighbors and decision tree below show the precision, recall, and f1 scores for label 0 (non-delinquent) and 1 (delinquent).


There is no silver bullet for choosing a model—often it comes down to the goals of implementation. In this situation, the tradeoff between identifying more delinquent loans at the cost of misclassification can be analyzed with a specific tool called a roc curve.  When the model predicts a class label, a probability threshold is used to make the decision. This threshold is set by default at 50% so that observations with more than a 50% chance of membership belong to one class and vice-versa.

The majority vote (of the neighbor observations or the leaf node observations) determines the predicted label. Roc curves allow us to see the impact of varying this voting threshold by plotting the true positive prediction rate against the false positive prediction rate for each threshold value between 0% and 100%.

The area under the ROC curve (AUC) quantifies the model’s ability to distinguish between delinquent and non-delinquent observations.  A completely useless model will have an AUC of .5 as the probability for each event is equal. A perfect model will have an AUC of 1 as it is able to perfectly predict each class.

To better illustrate, the ROC curves plotting the true positive and false positive rate on the held-out test set as the threshold is changed are plotted below.

7          Model Tuning

Up to this point the models have been built and evaluated using a single train/test split of the data. In practice this is often insufficient because a single split does not always provide the most robust estimate of the error on the test set. Additionally, there are more steps required for model tuning. To solve both of these problems it is common to train multiple instances of a model using cross validation. In K-fold cross validation, the training data that was first created gets split into a third dataset called the validation set. The model is trained on the training set and then evaluated on the validation set. This process is repeated times, each time holding out a different portion of the training set to validate against. Once the model has been tuned using the train/validation splits, it is tested against the held out test set just as before. As a general rule, once data have been used to make a decision about the model they should never be used for evaluation.

8          K-Nearest Neighbors Tuning

Below a grid search approach is used to tune the K-nearest neighbors model. The first step is to define all of the possible hyperparameters to try in the model. For the KNN model, the list nk = [10, 50, 100, 150, 200, 250] specifies the number of nearest neighbors to try in each model. The list is used by the function GridSearchCV to build a series of models, each using the different value of nk. By default, GridSearchCV uses 3-fold cross validation. This means that the model will evaluate 3 train/validate splits of the data for each value of nk. Also specified in GridSearchCV is the scoring parameter used to evaluate each model. In this instance it is set to the metric discussed earlier, the area under the roc curve. GridSearchCV will return the best performing model by default, which can then be used to generate predictions on the test set as before. Many more values of could be specified to search through, and the default minkowski distance could be set to a series of metrics to try. However, this comes at a cost of computation time that increases significantly with each added hyperparameter.


In the plot below the mean training and validation scores of the 3 cross-validated splits is plotted for each value of K. The plot indicates that for the lower values of the model was overfitting the training data and causing lower validation scores. As increases, the training score lowers but the validation score increases because the model gets better at generalizing to unseen data.

9               Random Forest Tuning

There are many hyperparameters that can be adjusted to tune the random forest model. We use three in our example: n_estimatorsmax_features, and min_samples_leafN_estimators refers to the number of trees to be created. This value can be increased substantially, so the search space is set to list estimators. Random Forests are generally very robust to overfitting, and it is not uncommon to train a classifier with more than 1,000 trees. Second, the number of variables to be randomly considered at each split can be tuned via max_features. Having a smaller value for the number of random features is helpful for decorrelating the trees in the forest, which is especially useful when multicollinearity is present. We tried a number of different values for max_features, which can be found in the list features. Finally, the number of observations required in each leaf node is tuned via the min_samples_leaf parameter and list samples.


The resulting plot, below, shows a subset of the grid search results. Specifically, it shows the mean test score for each number of trees and leaf size when the number of random features considered at each split is limited to 5. The plot demonstrates that the best performance occurs with 500 trees and a requirement of at least 5 observations per leaf. To see the best performing model from the entire grid space the best estimator method can be used.

By default, parameters of the best estimator are assigned to the GridSearch object (cvknc and cvrfc). This object can now be used generate future predictions or predicted probabilities. In our example, the tuned models are used to generate predicted probabilities on the held out test set. The resulting

ROC curves show an improvement in the KNN model from an AUC of .62 to .75. Likewise, the tuned Random Forest AUC improves from .64 to .77.

Predicting loan delinquency using only origination data is not an easy task. Presumably, if significant signal existed in the data it would trigger a change in strategy by MBS investors and ultimately origination practices. Nevertheless, this exercise demonstrates the capability of a machine learning approach to deconstruct such an intricate problem and suggests the appropriateness of using machine learning model to tackle these and other risk management data challenges relating to mortgages and a potentially wide range of asset classes.

Talk Scope

Big Data in Small Dimensions: Machine Learning Methods for Data Visualization

Analysts and data scientists are constantly seeking new ways to parse increasingly intricate datasets, many of which are deemed “high dimensional”, i.e., contain many (sometimes hundreds or more) individual variables. Machine learning has recently emerged as one such technique due to its exceptional ability to process massive quantities of data. A particularly useful machine learning method is t-distributed stochastic neighbor embedding (t-SNE), used to summarize very high-dimensional data using comparatively few variables. T-SNE visualizations allow analysts to identify hidden structures that may have otherwise been missed.

Traditional Data Visualization

The first step in tackling any analytical problem is to develop a solid understanding of the dataset in question. This process often begins with calculating descriptive statistics that summarize useful characteristics of each variable, such as the mean and variance. Also critical to this pursuit is the use of data visualizations that can illustrate the relationships between observations and variables and can identify issues that must be corrected. For example, the chart below shows a series of pairwise plots between a set of variables taken from a loan-level dataset. Along the diagonal axis the distribution of each individual variable is plotted.

The plot above is useful for identifying pairs of variables that are highly correlated as well as variables that lack variance, such as original loan term. When dealing with a larger number of variables, heatmaps like the one below can summarize the relationships between the data in a compact way that is also visually intuitive.

The statistics and visualizations described so far are helpful for summarizing and identifying issues, but they often fall short in telling the entire narrative of the data. One issue that remains is a lack of understanding of the underlying structure of the data. Gaining this understanding is often key to selecting the best approach for problem solving.

Enhanced Data Visualization with Machine Learning

Humans can visualize observations plotted with up to three variables (dimensions), but with the exponential rise in data collection it is now abnormal to only be dealing with a handful of variables. Thankfully, there are new machine learning methods that can help overcome our limited capacity and deliver new insights never seen before.

T-SNE is a type of non-linear dimensionality reduction algorithm. While this is a mouthful, the idea behind it is straightforward: t-SNE takes data that exists in very high dimensions and produces a plot in two or three dimensions that can be observed. The plot in low dimensions is created in such a way that observations close to each other in high dimensions remain close together in low dimensions. Additionally, t-SNE has proven to be good at preserving both the global and local structures present within the data1, which is of critical importance.

The full technical details of t-SNE are beyond the scope of this blog, but a simplified version of the steps for t-SNE are as follows:

  1. Compute the Euclidean distance between each pair of observations in high-dimensional space.
  2. Using a Gaussian distribution, convert the distance between each pair of observations into a probability that represents similarity between the points.
  3. Randomly place the observations into low-dimensional space (usually 2 or 3).
  4. Compute the distance and similarity (as in steps 1 and 2) for each pair of observations in the low-dimensional space. Crucially, in this step a Student t-distribution is used instead of a normal Gaussian.
  5. Using gradient based optimization, iteratively nudge the observations in the low-dimensional space in such a way that the probabilities between pairs of observations are as close as possible to the probabilities in high dimensions.

Two key consideration are the use of the Student t-distribution in step four as opposed to the Gaussian in step two, and the random initialization of the data points in low dimensional space. The t-distribution is critical to the success of the algorithm for multiple reasons, but perhaps most importantly in that it allows clusters that initially start far apart to re-converge2. Given the random initialization of the points in low dimensional space, it is common practice to run the algorithm multiple times with the same parameters to observe the best mapping and ensure that the gradient descent optimization does not get stuck in a local minima.

We applied t-SNE to a loan-level dataset comprised of approximately 40 variables. The loans are a random sample of originations from every quarter dating back to 1999. T-SNE was used to map the data into just three dimensions and the resulting plot was color-coded based on the year of origination.

In the interactive visualization below many clusters emerge. Rotating the figure reveals that some clusters are comprised predominantly of loans within similar origination years (groups of same-colored data points). Other clusters are less well-defined or contain a mix of origination years. Using this same method, we could choose to color loans with other information that we may wish to explore. For example, a mapping showing clusters related to delinquencies, foreclosure, or other credit loss events could prove tremendously insightful. For a given problem, using information from a plot such as this can enhance the understanding of the problem separability and enhance the analytical approach.

Crucial to the t-SNE mapping is a parameter set by the analyst called perplexity, which should be roughly equal to the number of expected nearby neighbors for each data point. Therefore, as the value of perplexity increases, the number of resulting clusters should generally decrease and vice versa. When implementing t-SNE, various perplexity parameters should be tried as the appropriate value is generally not known beforehand. The plot below was produced using the same dataset as before but with a larger value of perplexity. In this plot four distinct clusters emerge, and within each cluster loans of similar origination years group closely together.

Private-Label Securities – Technological Solutions to Information Asymmetry and Mistrust

At its heart, the failure of the private-label residential mortgage-backed securities (PLS) market to return to its pre-crisis volume is a failure of trust. Virtually every proposed remedy, in one way or another, seeks to create an environment in which deal participants can gain reasonable assurance that their counterparts are disclosing information that is both accurate and comprehensive. For better or worse, nine-figure transactions whose ultimate performance will be determined by the manner in which hundreds or thousands of anonymous people repay their mortgages cannot be negotiated on the basis of a handshake and reputation alone. The scale of these transactions makes manual verification both impractical and prohibitively expensive. Fortunately, the convergence of a stalled market with new technologies presents an ideal time for change and renewed hope to restore confidence in the system.


Trust in Agency-Backed Securities vs Private-Label Securities

Ginnie Mae guaranteed the world’s first mortgage-backed security nearly 50 years ago. The bankers who packaged, issued, and invested in this MBS could scarcely have imagined the technology that is available today. Trust, however, has never been an issue with Ginnie Mae securities, which are collateralized entirely by mortgages backed by the federal government—mortgages whose underwriting requirements are transparent, well understood, and consistently applied.

Further, the security itself is backed by the full faith and credit of the U.S. Government. This degree of “belt-and-suspenders” protection afforded to investors makes trust an afterthought and, as a result, Ginnie Mae securities are among the most liquid instruments in the world.

Contrast this with the private-label market. Private-label securities, by their nature, will always carry a higher degree of uncertainty than Ginnie Mae, Fannie Mae, and Freddie Mac (i.e., “Agency”) products, but uncertainty is not the problem. All lending and investment involves uncertainty. The problem is information asymmetry—where not all parties have equal access to the data necessary to assess risk. This asymmetry makes it challenging to price deals fairly and is a principal driver of illiquidity.


Using Technology to Garner Trust in the PLS Market

In many transactions, ten or more parties contribute in some manner to verifying and validating data, documents, or cash flow models. In order to overcome asymmetry and restore liquidity, the market will need to refine (and in some cases identify) technological solutions to, among other challenges, share loan-level data with investors, re-envision the due diligence process, and modernize document custody.


Loan-Level Data

During SFIG’s Residential Mortgage Finance symposium last month, RiskSpan moderated a panel that featured significant discussion around loan-level disclosures. At issue was whether the data required by the SEC’s Regulation AB provided investors with all the information necessary to make an investment decision. Specifically debated was the mortgaged property’s zip code, which provides investors valuable information on historical valuation trends for properties in a given geographic area.

Privacy advocates question the wisdom of disclosing full, five-digit zip codes. Particularly in sparsely populated areas where zip codes contain a relatively small number of addresses, knowing the zip code along with the home’s sale price and date (which are both publicly available) can enable unscrupulous data analysts to “triangulate” in on an individual borrower’s identity and link the borrower to other, more sensitive personal information in the loan-level disclosure package.

The SEC’s “compromise” is to require disclosing only the first two digits of the zip code, which provide a sense of a property’s geography without the risk of violating privacy. Investors counter that two-digit zip codes do not provide nearly enough granularity to make an informed judgment about home-price stability (and with good reason—some entire states are covered entirely by a single two-digit zip code).

The competing demands of disclosure and privacy can be satisfied in large measure by technology. Rather than attempting to determine which individual data fields should be included in a loan-level disclosure (and then publishing it on the SEC’s EDGAR site for all the world to see) the market ought to be able to develop a technology where a secure, encrypted, password-protected copy of the loan documents (including the loan application, tax documents, pay-stubs, bank statements, and other relevant income, employment, and asset verifications) is made available on a need-to-know basis to qualified PLS investors who share in the responsibility for safeguarding the information.


Due Diligence Review

Technologically improving the transparency of the due diligence process to investors may also increase investor trust, particularly in the representation and warranty review process. Providing investors with a secure view of the loan-level documentation used to underwrite and close the underlying mortgage loan, as described above, may reduce the scope of due diligence review as it exists in today’s market. Technology companies, which today support initiatives such as Fannie Mae’s “Day 1 Certainty” program, promise to further disrupt the due diligence process in the future. Through automation, the due diligence process becomes less burdensome and fosters confidence in the underwriting process while also reducing costs and bringing representation and warranty relief.

Today’s insistence on 100% file reviews in many cases is perhaps the most obvious evidence of the lack of trust across transactions. Investors will likely always require some degree of assurance that they are getting what they pay for in terms of collateral. However, an automated verification process for income, assets, and employment will launch the industry forward with investor confidence. Should any reconciliation of individual loan file documentation with data files be necessary, results of these reconciliations could be automated and added to a secure blockchain accessible only via private permissions. Over time, investors will become more comfortable with the reliability of the electronic data files describing the mortgage loans submitted to them.

The same technology could be implemented to allow investors to view supporting documents when reps and warrants are triggered and a review of the underlying loan documents needs to be completed.


Document Custody

Smart document technologies also have the potential to improve the transparency of the document custody process. At some point the industry is going to have to move beyond today’s humidity-controlled file cabinets and vaults, where documents are obtained and viewed only on an exception basis or when loans are paid off. Adding loan documents that have been reviewed and accepted by the securitization’s document custodian to a secure, permissioned blockchain will allow investors in the securities to view and verify collateral documents whenever questions arise without going to the time and expense of retrieving paper from the custodian’s vault.


Securitization makes mortgages and other types of borrowing affordable for a greater population by leveraging the power of global capital markets. Few market participants view mortgage loan securitization dominated by government corporations and government-sponsored enterprises as a desirable permanent solution. Private markets, however, are going to continue to lag markets that benefit from implicit and explicit government guarantees until improved processes, supported by enhanced technologies, are successful in bridging gaps in trust and information asymmetry.

With trust restored, verified by technology, the PLS market will be better positioned to support housing financing needs not supported by the Agencies.

Get a Demo

Tuning Machine Learning Models

Tuning is the process of maximizing a model’s performance without overfitting or creating too high of a variance. In machine learning, this is accomplished by selecting appropriate “hyperparameters.”

Hyperparameters can be thought of as the “dials” or “knobs” of a machine learning model. Choosing an appropriate set of hyperparameters is crucial for model accuracy, but can be computationally challenging. Hyperparameters differ from other model parameters in that they are not learned by the model automatically through training methods. Instead, these parameters must be set manually. Many methods exist for selecting appropriate hyperparameters. This post focuses on three:

  • Grid Search
  • Random Search
  • Bayesian Optimization

Grid Search

Grid Search, also known as parameter sweeping, is one of the most basic and traditional methods of hyperparametric optimization. This method involves manually defining a subset of the hyperparametric space and exhausting all combinations of the specified hyperparameter subsets. Each combination’s performance is then evaluated, typically using cross-validation, and the best performing hyperparametric combination is chosen.

For example, say you have two continuous parameters α and β, where manually selected values for the parameters are the following:


Then the pairing of the selected hyperparametric values, H, can take on any of the following:

Grid search will examine each pairing of α and β to determine the best performing combination. The resulting pairs, H, are simply each output that results from taking the Cartesian product of α and β. While straightforward, this “brute force” approach for hyperparameter optimization has some drawbacks. Higher-dimensional hyperparametric spaces are far more time consuming to test than the simple two-dimensional problem presented here. Also, because there will always be a fixed number of training samples for any given model, the model’s predictive power will decrease as the number of dimensions increases. This is known as Hughes phenomenon.

Random Search

Random search methods resemble grid search methods but tend to be less expensive and time consuming because they do not examine every possible combination of parameters. Instead of testing on a predetermined subset of hyperparameters, random search, as its name implies, randomly selects a chosen number of hyperparametric pairs from a given domain and tests only those. This greatly simplifies the analysis without significantly sacrificing optimization. For example, if the region of hyperparameters that are near optimal occupies at least 5% of the grid, then random search with 60 trials will find that region with high probability (95%).

equation 2.PNG

To illustrate, imagine a 15 x 30 grid of two hyperparameter values and their resulting scores ranging from 0-10, where 10 is the most optimal hyperparametric pairing (Table 1).

Table 1 – Grid of Hyperparameter Values and Scores

Highlighted in green are the 21 pairings with the highest scores out of the 450 total combinations. Let’s take these 21 pairings to be our desired target range. What if we were to sample points from this grid to see if any lands within the target? Each random draw has a 21/450 ≈ 4.67% of doing so. If we randomly select 60 points, all independent of one another, then the probability that none of them land in the target, or in other words all of them miss, is
equation 3.PNG

Therefore, the probability that at least one of them succeeds in hitting the desired interval is 1 minus that quantity.

In this particular example, sampling just 60 points from our hyperparameter space yields over a 94% chance of selecting a hyperparameter value within our desired interval near the maximum value.  In other words, in a scenario with a 5% desired interval around the true maximum, sampling just 60 points will yield a sufficient hyperparameter pairing 95% of the time.

There are two main benefits to using the random search method. The first is that a budget can be chosen independent of the number of parameters and possible values. Based on how much time and computing resources you have available, random search allows you to choose a sample size that conforms to a budget but still allows for a representative sample of the hyperparameter space. The second benefit is that adding parameters that do not influence performance does not decrease efficiency.

Bayesian Optimization

The idea behind Bayesian Optimization is fundamentally different from grid and random search. This process builds a probabilistic model for a given function and analyzes this model to make decisions about where to next evaluate the function. There are two main components under the Bayesian optimization framework.

  • A prior function that captures the behavior of the unknown objective function and an observation model that describes the data generation mechanism.
  • A loss function, or an acquisition function, that describes how optimal a sequence of queries are, usually taking the form of regret.

The most common selection for a prior function in Bayesian Optimization is the Gaussian process (GP) prior. This is a particular kind of statistical model where observations occur in a continuous domain. In a Gaussian process, every point in the defined continuous input space is associated with a normally distributed random variable. Additionally, every finite linear combination of those random variables has a multivariate normal distribution.

There are a number of options when choosing an acquisition function. Choosing an acquisition function requires choosing a trade-off in exploration of the entire search space vs. exploitation of current promising areas.

Probability of Improvement

One approach is to choose an improvement-based acquisition function, which favors points that are likely to improve upon an incumbent target. This strategy involves maximizing the probability of improving (PI) over the best current value. If using a Gaussian posterior distribution, this can be calculated as follows:

equation 5.PNG


equation 6.PNG

In each iteration, the probability of improving is maximized to select the next query point. Although the probability of improvement can perform very well when the target is known, using this method for an unknown target causes the PI to lose reliability.

Expected Improvement

Another strategy involves the case of attempting to maximize the expected improvement (EI) over the current best. Unlike the probability of improvement function, the expected improvement also incorporates the amount of improvement. Assuming a Gaussian process, this can be calculated as follows:

equation 7.PNG

Gaussian Process Upper Confidence Bound

Another method takes the idea of exploiting lower confidence bounds (upper when considering the maximization) to construct acquisition functions that minimize regret over the course of their optimization. This requires the user to define an additional tuning value, . This lower confidence bound (LCB) for a Gaussian process is defined as follows:

equation 8.PNG

There are a few limitations to consider when choosing Bayesian Optimization over other hyperparameter optimization methods. The power of the Gaussian process depends highly on the covariance function, and it is not always clear what the appropriate covariance function choice should be. Another factor to consider is that the function evaluation itself may involve a time-consuming optimization procedure. It’s important to find the best hyperparameters for your model, but in many cases, the complexity associated with finding the best hyperparameters using Bayesian Optimization may exceed the project’s established budget. If possible, one should always consider utilizing parallel computing when performing this technique to maximize computing resources and cut back on time.


Choosing an appropriate set of hyperparameters is crucial for machine learning model accuracy. We have discussed three different approaches for selecting hyperparameter values and the trade-offs associated with choosing one optimization method over another. Time, budget, and computing abilities are all factors to consider when choosing a method. Small hyperparameter spaces and lax restraints for budget and computing resources may make Grid Search the best option. For larger hyperparameter spaces or more computing constraints, a simple random search with a sufficient sample size or a Bayesian optimization technique may be more appropriate.

Get Started
Get A Demo

Linkedin    Twitter    Facebook