Linkedin    Twitter   Facebook

Get Started
Log In

Linkedin

Articles Tagged with: Innovation and Alternative Data

Chart of the Month: Tracking Mortgage Delinquency Against Non-traditional Economic Indicators by MSA

Tracking Mortgage Delinquency Against Non-traditional Economic Indicators by MSA 

Traditional economic indicators lack the timeliness and regional granularity necessary to track the impact of COVID-19 pandemic on communities across the country. Unemployment reports published by the Bureau of Labor Statistics, for example, tend to have latency issues and don’t cover all workers. As regional economies attempt to get back to a new “normal” RiskSpan has begun compiling non-traditional “alternative” data that can provide a more granular and real-time view of issues and trends. In past crises, traditional macro indicators such as home price indices and unemployment rates were sufficient to explain the trajectory of consumer credit. However, in the current crisis, mortgage delinquencies are deteriorating more rapidly with significant regional dispersion. Serious mortgage delinquencies in the New York metro region were around 1.1% by April 2009 vs 30 day delinquencies at 9.9% of UPB in April 2020.  

STACR loan–level data shows that nationwide 30–day delinquencies increased from 0.8% to 4.2% nationwide. In this chart we track the performance and state of employment of 5 large metros (MSA). 

May Chart of the Month


Indicators included in our Chart of the Month: 

Change in unemployment is the BLS measure computed from unemployment claims. Traditionally this indicator has been used to measure economic health of a region. BLS reporting typically lags by months and weeks. 

Air quality index is a measure we calculate using level PM2.5 reported by EPA’s AirNow database on a daily basis. This metric is a proxy of increased vehicular traffic in different regions. Using a nationwide network of monitoring sites, EPA has developed ambient air quality trends for particle pollution, also called Particulate Matter (PM). We compute the index as daily level of PM2.5 vs the average of the last 5 years.  For regions that are still under a shutdown air quality index should be less than 100 (e.g. New York at 75% vs Houston at 105%) 

Air pollution from traffic has increased in regions where businesses have opened in May ’20 (e.g. LA went up from 69% in April to 98% in May).  However, consumer spending has not always increased at the same level.  We look to proxies for hourly employment levels. 

New Daily COVID-19 Cases: This is a health crisis and managing the rate of new COVID-19 cases will drive decisions to open or close businesses. The chart reports the monthly peak in new cases using daily data from Opportunity Insight 

Hourly Employment and Hours Worked at small businesses is provided by Opportunity Insight using data from Homebase. Homebase is a company that provides virtual scheduling and time-tracking tools, focused on small businesses in sectors such as retail, restaurant, and leisure/accommodation. The chart shows change in level of hourly employment as compared to January 2020. We expect this is to be a leading indicator of employment levels for this sector of consumers. 


Sources of data: 

Freddie Mac’s (STACR) transaction database 

Opportunity Insight’s Recovery Tracker 

Bureau of Labor and Statistics (BLS)’ MSA level economic reports 

Environment Protection Agency (EPA)’s AirNow database. 


Webinar: 2020 — Entering The Decade of Data & Smart Analytics

webinar

2020 — Entering The Decade of Data & Smart Analytics

Prepare for the decade where data and analytics become the driving force behind successful investment management

For the first time in decades, Structured Finance is poised to join the rest of the financial sector in adopting new tech solutions. Deal cycles are shrinking from 3 weeks to as little as 2 days. Consequently, the market’s demand for granular collateral data has never been stronger. Accuracy and consistency are paramount. The new decade promises major advances in technology around data supporting investment best practices. Will you be ready to adopt them? 

Join industry veterans and RiskSpan executives Bill Moretti, Suhrud Dagli, and Bernadette Kogler for our latest webinar, 2020: Entering The Decade of Data & Smart Analytics.

RiskSpan, Inc. needs the contact information you provide to us to contact you about our products and services. You may unsubscribe from these communications at anytime. For information on how to unsubscribe, as well as our privacy practices and commitment to protecting your privacy, check out our Privacy Policy. Your privacy is important to us and your information will be kept confidential.

Key Topics:

  • Automation – How can you join asset managers aggressively seeking yield through automation? 
  • Prioritization – Which new tech will have the biggest impact on your workflow? 
  • Fit – How will you fit into the new Structured Finance ecosystem for the next decade?
  • Resistance – What has prevented the industry from adopting new tech in past decades? What has changed?


About The Hosts

Bernadette Kogler

CEO

Bernadette is co-founder, board member, and the Chief Executive Officer of RiskSpan. She is also co-founder of SmartLink Lab, RiskSpan’s innovation lab developing blockchain applications in lending and structured finance. Bernadette is an entrepreneurial leader focused on leveraging emerging technology for the advancement of data analytics and business process in the lending and structured finance markets. She leads the company’s long-term vision and strategy bringing deep expertise across the entire lending lifecycle. She is a seasoned executive and has spent most of her career focused on analytics, risk management and technology applications that provide strategic advantage to clients. Bernadette was previously with KPMG’s Mortgage and Structured Finance Practice and started her career with Prudential Insurance Company. She holds a BS in Finance from Villanova University and an MBA from Seton Hall University.  

Suhrud Dagli

CTO

Suhrud is a co-founder, board member, and the Chief Technology and Innovation Officer of RiskSpan. He is also co-founder of SmartLink Lab, an innovation lab developing blockchain applications for structured finance and the capital markets. Suhrud is one of the industry’s most respected experts in mortgage and structured product technology and leads RiskSpan’s technology strategy including the company’s SaaS offering, open source and API strategies. He is also responsible for RiskSpan’s advanced technology incubations including machine learning applications and applications developed with blockchain. Suhrud has spent his career developing solutions for the capital markets. Formerly he was Head of System & Analytics at Greenwich Capital and Head of Analytics and Model Development for UBS. Suhrud holds an MS in Computer Science from Pennsylvania State University and a BS in Electrical Engineering from VJTI, Bombay India.  

Bill Moretti, CFA, CPA, FRM

Senior Managing Director

Bill Moretti has over 30 years of experience identifying business opportunities and developing creative investment strategies & solutions for the Structured Finance industry on both the buy- and sell-sides. Bill’s expertise covers all sectors within structured finance including Agency Residential Mortgage Backed Securities (RMBS), Non-Agency RMBS, Asset Backed Securities (ABS), Collateralized Loan Obligations (CLO’s), and Commercial Mortgage Backed Securities (CMBS). In his new role as a Senior Managing Director and Lead of the Innovation Lab with RiskSpan, Bill with be focused on applications of machine learning, AI and Blockchain to improve efficiencies in lending, structured finance and the investment process. Bill holds a Bachelors of Business Administration (BBA) from Pace University in New York, NY, as well as CPA, CFA, and FRM designations.


Webinar: Machine Learning in Building a Prepayment Model

webinar

Machine Learning in Building a Prepayment Model

Join RiskSpan financial model experts Janet Jozwik, Fan Zhang, and Lei Zhao to discuss how machine learning can help simplify prepayment models. They will discuss

  • Data:  Preprocessing the data and determining which variables are important to include in prepayment models
  • Modeling Approach:  Evaluating machine learning approaches
  • Model Performance: Opening the black box and tuning the model to improve performance


About The Hosts

Janet Jozwik

Managing Director – RiskSpan

Janet Jozwik helps manage quantitative modeling and data analysis groups at RiskSpan. Janet has a background in mortgage credit modeling, loss forecasting, and data analysis. Since joining RiskSpan, Janet has focused on loss forecasting and mortgage portfolio analytics for a key client as well as building a credit model using GSE loan-level data. Prior to joining RiskSpan, Janet was a financial economist at Fannie Mae where she specialized in single family credit pricing. Her work directly impacted the national guarantee fee pricing scheme and government programs to support the housing market during and after the financial crisis. Janet has extensive experience in analyzing massive datasets, a deep understanding of the drivers of credit risk, and an expertise in modeling mortgage cash flows. Janet holds an MBA from the University Of Chicago Booth School Of Business and a BA in Economics from Johns Hopkins University. 

Fan Zhang

Director of Model Development

Fan Zhang has 12 years of quantitative finance experience specializing in behavioral modeling, fixed income analysis and, machine learning. At RiskSpan, Fan leads the quantitative modeling team where he is currently driving improvements to prepay modeling and application of cutting edge machine learning methods. Fan was a senior quantitative manager at Capital One where he worked on prepayment, deposit, MSR, auto, interest rate term structure, and economic capital modeling. He was also a senior financial engineer at Fannie Mae managing a team to validate model implementation and risk analytics. Fan holds an MBA from the University of Maryland and a BA in Economics from the University of Michigan.

Lei Zhao

Quantitative Modeling Analyst

Lei Zhao is a key member of the quantitative modeling team at RiskSpan. Lei has done extensive research on clustering methodologies and his postdoctoral research paper has been cited over a hundred times in scholarly publications. Lei holds a Master of Science degree in Financial Engineering from University of California, Los Angeles, and a PhD in Mechanical Engineering from Zhejiang University, China. 


Webinar: Using Machine Learning in Whole Loan Data Prep

webinar

Using Machine Learning in Whole Loan Data Prep

Tackle one of your biggest obstacles: Curating and normalizing multiple, disparate data sets.

Learn from RiskSpan experts:

  • How to leverage machine learning to help streamline whole loan data prep
  • Innovative ways to manage the differences in large data sets
  • How to automate ‘the boring stuff’


About The Hosts

LC Yarnelle

Director – RiskSpan

LC Yarnelle is a Director with experience in financial modeling, business operations, requirements gathering and process design. At RiskSpan, LC has worked on model validation and business process improvement/documentation projects. He also led the development of one of RiskSpan’s software offerings, and has led multiple development projects for clients, utilizing both Waterfall and Agile frameworks.  Prior to RiskSpan, LC was as an analyst at NVR Mortgage in the secondary marketing group in Reston, VA, where he was responsible for daily pricing, as well as on-going process improvement activities.  Before a career move into finance, LC was the director of operations and a minority owner of a small business in Fort Wayne, IN. He holds a BA from Wittenberg University, as well as an MBA from Ohio State University. 

Matt Steele

Senior Analyst – RiskSpan

LC Yarnelle is a Director with experience in financial modeling, business operations, requirements gathering and process design. At RiskSpan, LC has worked on model validation and business process improvement/documentation projects. He also led the development of one of RiskSpan’s software offerings, and has led multiple development projects for clients, utilizing both Waterfall and Agile frameworks.  Prior to RiskSpan, LC was as an analyst at NVR Mortgage in the secondary marketing group in Reston, VA, where he was responsible for daily pricing, as well as on-going process improvement activities.  Before a career move into finance, LC was the director of operations and a minority owner of a small business in Fort Wayne, IN. He holds a BA from Wittenberg University, as well as an MBA from Ohio State University. 


eBook: Machine Learning in Modeling Loan Data

ebook

Machine Learning in Modeling Loan Data

Understanding the challenges of implementing a machine learning solution is critical to yielding leverageable results. In this three part eBook, we cover the fundamentals of machine learning, a use case with modeling loan data as well as how machine learning can be used for data visualization.


Open Source and Mortgage Data Modeling

white paper

Open Source and Mortgage Data Modeling

Open source software is growing in popularity, but incorporating it into your organization can be daunting. Professionals are eager to apply it to their mortgage data analysis processes and reap its benefits, but are wary of its risks.

In this white paper, we share:

  • The benefits of open source that make it so popular
  • The risks inherent in open source and how to mitigate them
  • The application of open source to mortgage data analysis, including real examples from our own work



Imputation and Analysis with Machine Learning

white paper

Imputation and Analysis with Machine Learning

Despite industry-wide efforts to incorporate robust quality control programs, challenges with mortgage data persist. Fortunately, combining machine learning with cloud computing shows promise in addressing mortgage data gaps and producing more accurate results than traditional approaches. 

This white paper introduces two methods to impute missing values and understand the relationships between various features of a residential loan database.



eBook: Machine Learning in Model Risk Management

ebook

Machine Learning in Model Risk Management

In this eBook, we first address some of the ways in which machine learning techniques can be leveraged by model validators to assess models developed using conventional means. We then tackle several considerations that model validators should take into account when independently assessing machine learning models that appear in their inventories. 

In this eBook, you’ll learn:

  • Real-world examples illustrating how machine learning models can be used to solve financial problems
  • Procedures for validating machine learning models
  • Machine learning methods that can be applied during model validation to understand and mitigate model risk


Automate Your Data Normalization and Validation Processes

Robotic Process Automation (RPA) is the solution for automating mundane, business-rule based processes so that organizations high value business users can be deployed to more valuable work. 

McKinsey defines RPA as “software that performs redundant tasks on a timed basis and ensures that they are completed quickly, efficiently, and without error.” RPA has enormous savings potential. In RiskSpan’s experience, RPA reduces staff time spent on the target-state process by an average of 95 percent. On recent projects, RiskSpan RPA clients on average saved more than 500 staff hours per year through simple automation. That calculation does not include the potential additional savings gained from the improved accuracy of source data and downstream data-driven processes, which greatly reduces the need for rework. 

The tedious, error-ridden, and time-consuming process of data normalization is familiar to almost all organizations. Complex data systems and downstream analytics are ubiquitous in today’s workplace. Staff that are tasked with data onboarding must verify that source data is complete and mappable to the target system. For example, they might ensure that original balance is expressed as dollar currency figures or that interest rates are expressed as percentages with three decimal places. 

Effective data visualizations sometimes require additional steps, such as adding calculated columns or resorting data according to custom criteria. Staff must match the data formatting requirements with the requirements of the analytics engine and verify that the normalization allows the engine to interact with the dataset. When completed manually, all of these steps are susceptible to human error or oversight. This often results in a need for rework downstream and even more staff hours. 

Recently, a client with a proprietary datastore approached RiskSpan with the challenge of normalizing and integrating irregular datasets to comply with their data engine. The non-standard original format and the size of the data made normalization difficult and time consuming. 

After ensuring that the normalization process was optimized for automation, RiskSpan set to work automating data normalization and validation. Expert data consultants automated the process of restructuring data in the required format so that it could be easily ingested by the proprietary engine.  

Our consultants built an automated process that normalized and merged disparate datasets, compared internal and external datasets, and added calculated columns to the data. The processed dataset was more than 100 million loans, and more than 4 billion recordsTo optimize for speed, our team programmed a highly resilient validation process that included automated validation checks, error logging (for client staff review) and data correction routines for post-processing and post-validation. 

This custom solution reduced time spent onboarding data from one month of staff work down to two days of staff work. The end result is a fullyfunctional, normalized dataset that can be trusted for use with downstream applications. 

RiskSpan’s experience automating routine business processes reduced redundancies, eliminated errors, and saved staff time. This solution reduced resources wasted on rework and its associated operational risk and key-person dependencies. Routine tasks were automated with customized validations. This customization effectively eliminated the need for staff intervention until certain error thresholds were breached. The client determined and set these thresholds during the design process. 

RiskSpan data and analytics consultants are experienced in helping clients develop robotic process automation solutions for normalizing and aggregating data, creating routine, reliable data outputsexecuting business rules, and automating quality control testing. Automating these processes addresses a wide range of business challenges and is particularly useful in routine reporting and analysis. 

Talk to RiskSpan today about how custom solutions in robotic process automation can save time and money in your organization. 


Robotic Process Automation – Warehouse Line Reporting

Robotic Process Automation (RPA) is the solution for automating mundane, business-rule based processes so that your high value business users can be deployed to more valuable work.

McKinsey defines RPA as “software that performs redundant tasks on a timed basis and ensures that they are completed quickly, efficiently, and without error.” RPA has enormous savings potential. In RiskSpan’s experience, RPA reduces staff time spent on the target-state process by an average of 95 percent. On recent projects, RiskSpan RPA clients on average saved more than 500 staff hours per year through simple automation. That calculation does not include the potential additional savings gained from the improved accuracy of source data and downstream data-driven processes, which greatly reduces the need for rework.

Managing warehouse lines of credit pose a unique set of challenges to both lending and borrowing institutions. These lines revolve based on frequent, periodic transactions. The loan-level data underlying these transactions, while similar from one transaction to the next, are sufficiently nuanced to require individual review. These reviews are painstaking and can take an inordinate amount of time.

Recently, a consumer financing provider approached RiskSpan with the challenge of tracking its requests to a warehouse lender, so that it could better manage its warehouse loan portfolio. This client had a series of manual reporting processes that it ran upon each request to the warehouse lender to inform oversight of its portfolio. It needed assistance improving the accuracy and resource burden required to produce the reports.

RiskSpan responded to the challenge by completing a rapid RPA readiness assessment and by implementing automation to solve for the data challenges it uncovered. In the readiness assessment, RiskSpan deployed a consultant to ensure that the existing reports were enough to meet the needs of the organization; that source data was enough for the desired reporting; and that data transformation processes (people and systems) were maintaining data quality from input to output.

Once these processes were analyzed and a target-state was confirmed, RiskSpan consultants quickly got to work. We automated ingestion of data for two of the existing reports, automated high-value parts of the data normalization processes and created automated quality control tests for each report.

This custom solution reduced the cycle time from one hour of staff work to 5 minutes of staff work at each warehouse lender request. This saved more than two full weeks of staff time over the course of the year and dramatically increased the scalability of this valuable process.

RiskSpan’s experience automating routine business processes reduced redundancies, eliminated errors, and saved staff time. Our solution reduced resources wasted on rework and its associated operational risk and key-person dependencies. Routine tasks were automated with customized validations. This customization effectively eliminated the need for staff intervention until certain error thresholds were breached. The client determined and set these thresholds during the design process.

RiskSpan data and analytics consultants are experienced in helping clients develop robotic process automation solutions for normalizing and aggregating data, creating routine, reliable data outputs, executing business rules, and automating quality control testing. Automating these processes addresses a wide range of business challenges and is particularly useful in routine reporting and analysis.

Talk to RiskSpan today about how custom solutions in robotic process automation can save time and money in your organization.


Get Started
Log in

Linkedin   

risktech2024