The Client
Government Sponsored Enterprise (GSE)
The Problem
The client sought to improve the performance and forecasting capabilities of its loan valuation and forecast engine. As part of this strategic initiative, the client planned to migrate the underlying platform from Hadoop to the Snowflake Data Cloud to achieve an increase in data loading and querying speeds and an overall optimization of system performance.
RiskSpan identified a need for project management and implementation planning, as well as data pipeline and ETL migration analysis to ensure a successful integration of the Snowflake data cloud into the loan valuation and forecast engine.
The Solution
RiskSpan led the data migration effort for the loan valuation engine and integrated its pipelines from multiple data sources. The RiskSpan team also executed planning, testing, and overall project management of the implementation effort to ensure a high quality, on-schedule delivery.
The Deliverables
- An integrated project plan with transition from current state to target state and production parallel
- A system and data flow comparing existing state to target state
- SQL code to efficiently compare 13 million records and more than 100 attributes loaded to Snowflake with legacy data in just 2 minutes.
- Review of target state database ETL patterns
- Review of loan valuation engine output using data in Snowflake
- Comprehensive report presented to Senior Management
BACKGROUND
One of the nation’s largest mortgage loan and MSR investors was hampered by a complex data ingestion process as well as slow and cumbersome on-prem software for pricing and market risk.
A complicated data wrangling process was taking up significant time and led to delays in data processing. Further, month-end risk and financial reporting processes were manual and time-pressured. The data and risk teams were consumed with maintaining the day-to-day with little time available to address longer-term data strategies and enhance risk and modeling processes.
OBJECTIVES
-
Modernize Rithm’s mortgage loan and MSR data intake from servicers — improve overall quality of data through automated processes and development of a data QC framework that would bring more confidence in the data and associated use cases, such as for calculating historical performance.
-
Streamline portfolio valuation and risk analytics while enhancing granularity and flexibility through loan-level valuation/risk.
-
Ensure data availability for accounting, finance and other downstream processes.
-
Bring scalability and internal consistency to all of the processes above.
THE SOLUTION
THE EDGE WE PROVIDED
By adopting RiskSpan’s cloud-native data management, managed risk, and SaaS solutions, Rithm Capital saved time and money by streamlining its processes
Adopting Edge has enabled Rithm to access enhanced and timely data for better performance tracking and risk management by:
- Managing data on 5.5 million loans, including source information and monthly updates from loan servicers (with ability in the future to move to daily updates)
- Ingesting, validating and normalizing all data for consistency across servicers and assets
- Implementing automated data QC processes
- Performing granular, loan-level analysis
With more than 5 million mortgage loans spread across nine servicers, Rithm needed a way to consume data from different sources whose file formats varied from one another and also often lacked internal consistency. Data mapping and QC rules constantly had to be modified to keep up with evolving file formats.
Once the data was onboarded Rithm required an extraordinary amount of compute power to run stochastic paths of Monte Carlo rate simulations on all 4 million of those loans individually and then discount the resulting cash flows based on option adjusted yield across multiple scenarios.
To help minimize the computing workload, Rithm had been running all these daily analytics at a rep-line level—stratifying and condensing everything down to between 70,000 and 75,000 rep lines. This alleviated the computing burden but at the cost of decreased accuracy and limited reporting flexibility because results were not at the loan-level.
Enter RiskSpan’s Edge Platform.
Combining the strength of RiskSpan’s subject matter experts, quantitative analysts, and technologists together with the power of the Edge platform, RiskSpan has helped Rithm achieve its objectives across the following areas:
Data management and performance reporting
- Data intake and quality control for 9 servicers across loan and MSR portfolios
- Servicer data enrichment
- Automated data loads leading to reduced processing time for rolling tapes
- Ongoing data management support and resolution
- Historical performance review and analysis (portfolio and universe)
Valuation and risk
- Daily reporting of MSR, mortgage loan and security valuation and risk analytics based on customized Tableau reports
- MSR and whole loan valuation/risk calculated based at the loan-level leveraging the scalability of the cloud-native infrastructure
- Additional scenario analysis and other requirements needed for official accounting and valuation purposes
Interactive tools for portfolio management
- Fast and accurate tape cracking for purchase/sale decision support
- Ad-hoc scenario analyses based on customized dials and user-settings
The implementation of these enhanced data and analytics processes and increased ability to scale these processes has allowed Rithm to spend less time on day-to-day data wrangling and focus more on higher-level data analysis and portfolio management. The quality of data has also improved, which has led to more confidence in the data that is used across many parts of the organization.
Models + Data management = End-to-end Managed Process
”The economies of scale we have achieved by being able to consolidate all of our portfolio risk, interactive analytics, and data warehousing onto a single platform are substantial. RiskSpan’s experience with servicer data and MSR analytics have been particularly valuable to us.“
— Head of Analytics
Asset Manager | New York, NY
RiskSpan Applications Provided
GOVERNANCE
ABOUT THE CLIENT
A leading provider of capital and services to the mortgage and financial services industries that leverage their proven investment expertise and identity and invest in assets that offer attractive risk-adjusted returns while also protecting our existing portfolio and generating long-term value for our investors.
PROBLEM
An asset manager sought to replace an inflexible risk system provided by a Wall Street dealer. The portfolio was diverse, with a sizable concentration in structured securities and mortgage assets.
The legacy analytics system was rigid with no flexibility to vary scenarios or critical investor and regulatory reporting.
CHALLENGE
Lacked a single-solution
Data integrity issues
Inflexible locally installed risk management system
No direct connectivity to downstream systems
Models + Data management = End-to-end Managed Process
HIGHLIGHTS
5 Vendors → Single Platform
32% Annual Cost Savings
Increased Flexibility
Additional
SOLUTION
RiskSpan’s Edge Platform delivered a cost-efficient and flexible solution by bundling required data feeds, predictive models for mortgage and structured products, and infrastructure management.
The Platform manages and validates the asset manager’s third-party and portfolio data and produces scenario analytics in a secure hosted environment.
TESTIMONIAL
”Our existing daily process for calculating, validating, and reporting on key market and credit risk metrics required significant manual work… [Edge] gets us to the answers faster, putting us in a better position to identify exposures and address potential problems.”
— Managing Director, Securitized Products
EDGE PROVIDED
END-TO-END DATA AND RISK MANAGEMENT PLATFORM
- Scalable, cloud native technology
- Increased flexibility to run analytics at loan level; additional interactive / ad-hoc analytics
- Reliable accurate data with frequent updates
COST AND OPERATIONAL EFFICIENCIES GAINED
- Streamlined workflows | Automated processes
- 32% annual cost savings
- 46% fewer resources needed for maintenance
AT-A-GLANCE
An asset manager sought to replace an inflexible risk system provided by a Wall Street dealer. The portfolio was diverse, with a sizable concentration in structured securities and mortgage assets.
The legacy analytics system was rigid with no flexibility to vary scenarios or critical investor and regulatory reporting.
5 Vendors → Single Platform
32% Annual Cost Savings
Increased Flexibility
Additional Ad-hoc Analytics
”Our existing daily process for calculating, validating, and reporting on key market and credit risk metrics required significant manual work… [Edge] gets us to the answers faster, putting us in a better position to identify exposures and address potential problems.”
— Managing Director, Securitized Products
Models + Data management = End-to-end Managed Process
CHALLENGES
Lacked a single-solution
Data integrity issues
Inflexible locally installed risk management system
No direct connectivity to downstream systems
SOLUTIONS
RiskSpan’s Edge Platform delivered a cost-efficient and flexible solution by bundling required data feeds, predictive models for mortgage and structured products, and infrastructure management.
The Platform manages and validates the asset manager’s third-party and portfolio data and produces scenario analytics in a secure hosted environment.
EDGE WE PROVIDED
End-to-end data and risk management platform
- Scalable, cloud native technology
- Increased flexibility to run analytics at loan level; additional interactive / ad-hoc analytics
- Reliable accurate data with frequent updates
Cost and operational efficiencies gained
- Streamlined workflows | Automated processes
- 32% annual cost savings
- 46% fewer resources needed for maintenance
As a new MBS operation, this institutional broker-dealer needed trade capture and analytics functionality, particularly for risk management purposes. The broker-dealer also required an application to track MBS pass-through positions in real-time, given the active trading style of its pass-through desk (an average of 3 trades per minute).
The Solution
The client adopted the Edge Platform and RiskSpan provided custom development services that included:
- A real-time pass-through matrix Start-of-Day/ Intra-day firm-wide position upload (taking a feed from a proprietary books-and-records system)
- Real-time trade capture from Bloomberg and internal sources
The pass-though desk actively used the pass-through matrix for several years. When the client developed its own internal solution, it continued using the Edge Platform to run daily risk scenarios on the firm’s positions.
Total development time for all these projects was about 6 weeks.
A national property and casualty insurance carrier was struggling with an antiquated claims platform. Built on the IBM AS400 Mainframe system, the existing platform was unable to scale up to the growing needs of the organization and was based on legacy code plagued with significant “technical debt.”
The Solution
RiskSpan partnered with the client to identify and vet out a cloud-based SaaS solution provider to function as the system of record for all claims processed within the organization. This partnership ran from the discovery phase all the way through the production roll-out and post roll-out business-as-usual phase.
RiskSpan also assisted with the data migration ETL project necessary to transfer existing open and recent claims to the new platform. All existing interfaces with internal systems and third parties were reconfigured to be functional with the new claims platform.
Client Benefit
Cloud adoption enabled the client to improve its technology capability score from AM Best Ratings, a key metric for evaluating the health of insurance carriers.
Project deliverables included:
- Documentation of the current state of all internal and external interfaces
- Design and Solution Architecture for impacted interfaces
- API Design and Data Normalization across the Claims enterprise
- API Interfaces using Reactive Programming principles
- Implementation of the required security compliance for all data transmissions to and from the public cloud
- Integration with Azure identity systems for SSO Integration
- Automated Integration testing
- Data Lake on SQL Server to facilitate data migration
- Financial Reporting from Data Lake using Tableau Server
- Agile Project Delivery with 4-week sprints using SAFe Release Trains.
- Technology Stack – Java, Spring Cloud, Spring Boot, Spring Security, AS400 DataQueues, Azure SSO, JIRA, Jenkins, Gradle, OAuth 2, Tomcat, GIT, Gerrit, JSON, XML, SQL, Stored Procedures.
A national property and casualty insurance carrier needed to modernize its customer self–service portal. The complexity of the existing portal made it difficult for customers to find what they were looking for, resulting in declining customer engagement. The existing system was also inflexible and failed to align with the company’s new products and brand identity.
The Solution
RiskSpan led the development of a state-of-the-art, web-based application enabling customers to resolve a full range of self-service needs without resorting to a customer service call. The solution was developed using the Design Thinking approach, putting users first and offering a simplified and seamless experience when servicing policies.
Client Benefits
The technical architecture laid the foundation for all future web-based applications to be developed within the organization.
The new portal was sufficiently flexible to support rapid deployment of new features relating to the changing product landscape owing to increases in recent catastrophic events.
Other client deliverables included:
- Technical Architecture for the proposed JavaScript front-end platform which would be supported by a micro-services based backend system
- Proof of Concept delivery with Rapid Prototyping
- Implemented a React based Front end application with reusable component libraries
- Component libraries have been implemented in the organization’s new branding aesthetic and will be made available through an internal component repository that can be leveraged by all applications.
- Optimized solution to meet future performance demands and scaling to ensure a consistent user experience
- A/B Testing capabilities to ensure continual user engagement
- Agile Project Delivery with 2-week sprints using SAFe Release Trains
- Kanban Development adopted post production roll-out with interrupt capacity planning to rapidly address issues that might come up in production.
- Unified code-base to support application delivery over mobile apps as well
- Technology Stack – Typescript, React.js, React Native, Material UI, Redux, Java, Spring Boot, Spring Security, JIRA, Jenkins, Gradle, OAuth 2, Node.js, Tomcat, GIT, Gerrit, JSON.
One of the nation’s leading mortgage lenders had recently acquired several large MSR portfolios and required assistance reviewing, documenting and recommending enhancements to the underlying assumptions of the model used to price the MSR portfolios at acquisition.
Requiring review and documentation included collateral assumptions, cost and revenue assumptions, and prepayment (CDR/CRR/CPR) assumptions.
The Solution
RiskSpan comprehensively analyzed the cash flow impact of each major assumption (e.g., CDR/CRR/CPR, servicing advances, fees, cost) — the collateral assumptions in the model as well as documented forecast vs. actual outcomes.
RiskSpan worked in concert with the servicer’s finance and pricing teams to collect and analyze roll rates and to forecast actual loan-level data around losses, servicing advances, servicing fees, ancillary fees, PIF, and scheduled principal payments.
Deliverables
A comprehensive pricing model validation report that included the following:
- Consolidated CDR-, CRR-, CPR-related pricing model data, including balance, delinquency status, recapture, scheduled payments, default, etc. for all acquired portfolios. The resulting dataset could be used both for deal tracking and pricing model validation
- Documentation of the calculation and location of pricing model fields.
- Reconciliation of the different methods for calculating CDR, CRR, and CPR.
- Deep dives into model predictions of short sales and foreclosure turn-times
- Loan-state transition model forecasts and comparison of the model variables between two version of the forecast, including shift analyses.
- Drivers of forecast variance.
- Identification of dials responsible for short sale and foreclosure turn forecast shifting.
- SAS-based streamlined process for comparing model variables for sub-segment and sub-models in loan state
- Transition Model: Incorporation of actual and forecast into pricing models to compare with original pricing model cash flow results for acquired portfolios
- Creation and standardization of the pricing model validation report output.
- Automation of reporting.
- Improvement of the process by creating a calculation template that could be easily replicated for other portfolios.
- Documentation of the validation process and comprehensive review of the validation results with the servicer’s risk team, finance team and pricing team management.
A leading hedge fund administrator sought a better way to provide compliance reporting and overnight risk and portfolio reporting for its clients.
Reporting at this scale requires extraordinarily flexibility in computational bandwidth.
The Solution
RiskSpan delivered computation and distribution via the cloud of all required analytics and risk metrics to all relevant parties using the flexibility and attractive visualization of a seamless Tableau integration.
- Ingestion, validation, and integration of disparate data sources (rates, implied volatility data and terms and conditions from six data vendor sources)
- Reporting, distribution and publishing of the client’s full range of risk metrics, including VaR, custom aggregation, scenario analyses, interest rate shocks and other stress testing — all readily viewable to every client stakeholder via the cloud using Tableau.
The Edge We Provided
A fully hosted, outsourced solution. The administrator’s highly dynamic reports are delivered by way of a secure, hosted environment to a large number of diverse, institutional clients.
An institutional-broker dealer needed a solution to analyze agency MBS prepayment data.
The Solution
The Edge Platform has been adopted and is actively used by the Agency trading desk to analyze Agency MBS prepayment data, to discover relationships between borrower characteristics and prepayment behavior.