Linkedin    Twitter   Facebook

Get Started
Log In

Linkedin

Articles Tagged with: General

AI-Powered Code Reviews

Our firm recently implemented a pilot that promises to dramatically accelerate our developer workflow by leveraging AI in code reviews. Feedback is now instant and actionable – and available in the very environments where our developers work.

The Problem: Time-consuming pull requests

A pull request is a developer’s proposal (after writing code to solve an issue/feature/bug) to merge changes in one branch of a code repository into (usually) the main branch. The resulting merged code is what gets promoted to production.

This is generally how junior developers submit code changes for review by more senior developers. These code reviews are critical but eat up a lot of senior developer time. Senior developers at RiskSpan face many of the same challenges as senior developers everywhere in that they juggle multiple priorities and struggle to find the time necessary to provide thorough, timely feedback on every pull request. This can lead to delays, inconsistent quality, and “technical debt” over time.

The Solution: An AI Merge Agent

At AWS re:Invent, we discovered Qodo Merge, an AI-powered tool that automates and enhances pull request reviews. Now live in our Bitbucket repositories, Qodo Merge:

  • Analyzes code changes and autogenerates pull request descriptions
  • Checks ticket compliance to ensure requirements are met
  • Flags security risks (e.g., command injection, cross-site scripting)
  • Suggests improvements in data processing, error handling, and logic
  • Provides real-time feedback, accelerating development cycles

Why this matters for our development lifecycle

This AI solution is revolutionizing and streamlining RiskSpan’s software development process by:

  • Standardizing our code review best practices
  • Reducing technical debt by enforcing quality baselines
  • Accelerating junior developers and making them more efficient by providing instant guidance
  • Freeing up senior engineers to focus their efforts on high-impact strategic work

What’s Next?

Having completed our initial pilot testing, we are now rolling out Qodo Merge across RiskSpan’s various code repositories. Next up: training sessions and broader adoption across all of our modeling and engineering teams.

AI is transforming how we build, validate, and deploy code. Stay tuned for insights on how this initiative is improving our development speed and quality!


Transforming Loan Data Management Using Snowflake Secure Data Sharing

Presenters

Paul Gross

Senior Quantitative Analyst, Rithm Capital

Michael Cowley

Principal, Data Cloud Products, Snowflake

Bernadette Kogler

CEO, RiskSpan

Suhrud Dagli

CTO, RiskSpan

Wednesday, May 29th, 2024

1:00 ET

Hear from a distinguished panel including RiskSpan and Snowflake customers as they describe how Data Share has transformed their approach to mortgage investment. Specific topics to include:

  • High-speed data processing using Snowflake for easy delivery of risk analytics and diligence data
  • How Snowflake’s Data Sharing facilitates data access across and between organizations while maximizing computational performance and flexibility 
  • How Snowflake protects client data
  • The unique value of a central hub for all mortgage industry data and never having to FTP a file again

watch recording


Celebrating Women’s Contributions by the Numbers

Because we’re a data company after all. RiskSpan commemorates International Women’s Day by taking note of the remarkable people behind these numbers.

Martha Stewart

Votes for Women

Serena Williams

Women's March in DC

Girls Who Code

Title IX

Sally Ride

Womens Rights

Taylor Swift

Sandra Day O'connor

Kathryn Blgelow

Betty White


Connect with us at SFVegas 2024

Click Here to book a time to connect

RiskSpan is delighted to be sponsoring SFVegas 2024!

Connect with our team there to learn how we can help you move off your legacy systems, streamline workflows and transform your data.

SFA-Attendees
Click Here to book a time to connect

Don’t miss these RiskSpan presenters at SFVegas 2024

Bernadette Kogler

Housing Policy:
What’s Ahead
Mon, Feb 26th, 1:00 PM

Tom Pappalardo

Future of Fintech
Wed, Feb 28th, 9:15 AM

Divas Sanwal Photo (3)

Divas Sanwal

Big Data & Machine Learning: Impacts on Origination
Wed, Feb 28th, 11:05 AM

Can’t make the panels?

Click here to make an appointment to connect. Or just stop by Booth 13 in the exhibit hall!


Watch Suhrud Dagli Discuss AI in Securities Analytics at Chartis Research RiskTech100 Conference

Day 3 - 9.55 - Using AI in securities analytics
Watch Recording

(Register for Day 3)

Register to watch: www.risktech100.com


Snowflake Tutorial Series: Episode 3

Using External Tables Inside Snowflake to work with Freddie Mac public data (13 million loans across 116 fields)

Using Freddie Mac public loan data as an example, this five-minute tutorial succinctly demonstrates how to:

  1. Create a storage integration
  2. Create an external stage
  3. Grant access to stage to other roles in Snowflake
  4. List objects in a stage
  5. Create a format file
  6. Read/Query data from external stage without having to create a table
  7. Create and use an external table in Snowflake

This is the third in a 10-part tutorial series demonstrating how RiskSpan’s Snowflake integration makes mortgage and structured finance analytics easier than ever before.

Episode 1, Setting Up a Database and Uploading 28 Million Mortgage Loans, is available here.

Episode 2, Using Python User-Defined Functions in Snowflake SQL, is available here.

Future topics will include:

  • OLAP vs OLTP and hybrid tables in Snowflake
  • Time Travel functionality, clone and data replication
  • Normalizing data and creating a single materialized view
  • Dynamic tables data concepts in Snowflake
  • Data share
  • Data masking
  • Snowpark: Data analysis (pandas) functionality in Snowflake

RiskSpan’s Snowflake Tutorial Series: Ep. 2

Learn how to use Python User-Defined Functions in Snowflake SQL

Using CPR computation for a pool of mortgage loans as an example, this six-minute tutorial succinctly demonstrates how to:

  1. Query Snowflake data using SQL
  2. Write and execute Python user-defined functions inside Snowflake
  3. Compute CDR using Python UDF inside Snowflake SQL

This is this second in a 10-part tutorial series demonstrating how RiskSpan’s Snowflake integration makes mortgage and structured finance analytics easier than ever before.

Episode 1, Setting Up a Database and Uploading 28 Million Mortgage Loans, is available here.

Future topics will include:

  • External Tables (accessing data without a database)
  • OLAP vs OLTP and hybrid tables in Snowflake
  • Time Travel functionality, clone and data replication
  • Normalizing data and creating a single materialized view
  • Dynamic tables data concepts in Snowflake
  • Data share
  • Data masking
  • Snowpark: Data analysis (pandas) functionality in Snowflake

Prepayment Modeling: Today’s Housing Turnover Conundrum

Presenters

alex-fishbein

Alex Fishbein

Director, TD Securities

divas

Divas Sanwal

Head of Modeling, RiskSpan

raj-dosaj

Raj Dosaj

Chief Revenue Officer, RiskSpan

Recorded: Thursday, June 22

Accurately modeling the lock-in effect on housing turnover presents some unique challenges.

Join TD’s Alex Fishbein and RiskSpan’s Divas Sanwal as they discuss various approaches available to modelers for tackling these challenges.



Webinar Recording: An Investor’s Guide to America’s Housing Supply Crisis

Presenters

Amy Cutts

Amy Crews Cutts

President, AC Cutts and Associates and Chief Economist, NACM

michael-neal

Michael Neal

Equity Scholar and 
Principal Research Associate, Urban Institute

Janet Jozwik

Senior Managing Director and Head of Climate Analytics, RiskSpan

Divas Sanwal Photo (3)

Divas Sanwal

Managing Director and Head of Modeling, RiskSpan

Recorded: Wednesday, March 29th

An informative webinar on the nation’s current “out-of-whack” housing supply and what it means for mortgage investors, homeowners, prospective homebuyers, and renters alike!

Housing economists Amy Crews Cutts and Michael Neal join RiskSpan credit and prepayment modelers Janet Jozwik and Divas Sanwal as they explore the factors that contribute to the current housing supply imbalance, including the cost of building, the impact of permits and zoning, and the emergence of the “missing middle.” They discuss how high interest rates and rental prices are incentivizing owners who relocate to hold old on to their old properties and become landlords. They also examine the impact of ADUs, zoning issues, and the availability of renovation financing.

Mortgage loan and security investors will learn about what housing supply means for prepay speeds. The panelists will consider the role of financing in addressing housing supply issues, including the market for low-balance loans and unconventional options like contracts for deed and lease-to-own arrangements.

The panel discusses the evolving housing needs of the population, including the desire to age in place, the challenges posed by multigenerational living arrangements, and the viability of several proposed solutions, including the potential for converting unused commercial properties into housing.



RiskSpan Incorporates Flexible Loan Segmentation into Edge Platform

ARLINGTON, Va., March 3, 2023 — RiskSpan, a leading technology company and the most comprehensive source for data management and analytics for residential mortgage and structured products, has announced the incorporation of Flexible Loan Segmentation functionality into its award-winning Edge Platform.

The new functionality makes Edge the only analytical platform offering users the option of alternating between the speed and convenience of rep-line-level analysis and the unmatched precision of loan-level analytics, depending on the purpose of their analysis.

For years, the cloud-native Edge Platform has stood alone in its ability to offer the computational scale necessary to perform loan-level analyses and fully consider each loan’s individual contribution to a mortgage or MSR portfolio’s cash flows. This level of granularity is of paramount importance when pricing new portfolios, taking property-level considerations into account, and managing tail risks from a credit/servicing cost perspective.

Not every analytical use case justifies the computational cost of a full loan-level analysis, however. For situations where speed requirements dictate the use of rep lines (such as for daily or intra-day hedging needs), the Edge Platform’s new Flexible Loan Segmentation affords users the option to perform valuation and risk analysis at the rep line level.

Analysts, traders and investors take advantage of Edge’s flexible calculation specification to run various rate and HPI scenarios, key rate durations, and other calculation-intensive metrics in an efficient and timely manner. Segment-level results run at both loan and rep line level can be easily compared to assess the impacts of each approach. Individual rep lines are easily rolled up to quickly view results on portfolio subcomponents and on the portfolio as a whole.

Comprehensive details of this and other new capabilities are available by requesting a no-obligation demo at riskspan.com.

This new functionality is the latest in a series of enhancements that further the Edge Platform’s objective of providing frictionless insight to Agency MBS traders and investors, knocking down barriers to efficient, clear and data-driven valuation and risk assessment.

###

About RiskSpan, Inc. 

RiskSpan offers cloud-native SaaS analytics for on-demand market risk, credit risk, pricing and trading. With our data science experts and technologists, we are the leader in data as a service and end-to-end solutions for loan-level data management and analytics. Our mission is to be the most trusted and comprehensive source of data and analytics for loans and structured finance investments. Learn more at www.riskspan.com.


Get Started
Log in

Linkedin   

risktech2024