Consumer credit modelling software: SAS

 

Banks and fintechs want to provide consumers with consistent and contextual experiences across the credit lifecycle, placing greater demand on them to manage large, diverse datasets, develop state-of-the-art risk models and integrate analytics in decisioning processes, while meeting and maintaining model governance requirements.

The integrated SAS ecosystem supports the end-to-end credit lifecycle with best-in-class data management; easy and rapid development and deployment of risk models and decisions; and integrated governance of data and models, auditability and lineage. It has a variety of model explainability measures for machine learning and built-in bias and fairness metrics. Furthermore, the ecosystem offers pre-configured out-of-the-box content, including sample data models and model templates, ensuring compliance with regulations worldwide. SAS has broad capabilities in data preparation, data quality and analytics. Data engineers and scientists can access and onboard any data, including granular transactional, third-party, traditional or alternative data. They can develop a variety of models including statistical or modern machine learning risk models.

A critical market differentiator is the ease with which models can be deployed to any combination of in-memory, in-database, batch, real-time or streaming risk engines at the click of a button, eliminating the need for recoding. It provides a modernised decision-authoring tool for credit decision automation. SAS has built in a comprehensive set of model monitoring metrics for backtesting, benchmarking and compliance.

Terisa Roberts

SAS leverages a global pool of subject matter experts in consumer credit modelling, with experience of extensive implementations at large, multinational and regional banks. Additionally, they are actively collaborating with partners in consumer credit modelling to enrich technologies and expand domain knowledge.

The SAS platform has been enhanced with plentiful new capabilities including dynamic data preparation for risk modelling that allows for variable sharing, complex derivation logic and extract, transform and load (ETL) processing, exchange and redeployment. It offers a bespoke data engineering application for advanced ETL and lineage and support for in-database processing of risk models and decisions in Teradata.

The Covid-19 pandemic brought stress-testing to the forefront and put emphasis on assessing impacts on portfolios using a range of scenarios. This has transformed a compliance exercise to an essential management tool. In response, SAS has developed a scenario impact simulator to help banks better facilitate the forecasting of various stress scenarios through interactive analysis.

As demand for more and better models increases, firms are looking for more agility to make changes to models and policy rules and automate parts of the risk model lifecycle. Among other capabilities, SAS offers overlay models to support pre-pandemic models and policies, as well as new opportunities to capture and use transactional data. Another key response was to develop a risk modelling accelerator to help customers run analyses and test models to understand economic impacts of the pandemic.

The judges said:

• “Excellent entry and a very comprehensive and innovative response to the pandemic.”
• “Good to see a focus on easy and fast model deployment as well as natural language explainability.”
• “Great product and interesting additions to the service.”
• “SAS is a clear leader in this category – model as a service is innovative.”

Terisa Roberts, Global solution lead, risk modelling and decisioning at SAS, said:

“We are delighted to have won this award for our consumer credit modelling solution, which reflects SAS’s unparalleled expertise in this space. We continue to build on our extensive experience, helping large banks with a wide range of implementations, from enterprise decisioning to accelerated model development and deployment lifecycles.” 

Sponsored content