Banks and fintechs want to provide consumers with consistent and contextual experiences across the credit lifecycle, asking more of them to manage large, diverse data sets, develop advanced risk models, and integrate analytics into decision-making 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 management of data and models, verifiability and lineage. It has a variety of model explainability measures for machine learning and built-in bias and fairness metrics. In addition, the ecosystem provides preconfigured out-of-the-box content, including sample data models and model templates, ensuring global regulatory compliance. SAS has broad capabilities in the field of data preparation, data quality and analysis. Data engineers and scientists have access to all data, including detailed transaction data, third-party data, traditional or alternative data. They can develop different models, including statistical or modern machine learning risk models.
A key differentiator in the market is the ease with which models can be deployed at the touch of a button for any combination of in-memory, in-database, batch, real-time or streaming risk engines, eliminating the need for recoding. It provides a modernized decision-making tool for automating credit decisions. SAS has built-in a comprehensive set of model monitoring metrics for backtesting, benchmarking, and compliance.
SAS leverages a global pool of consumer credit modeling subject matter experts, with experience in extensive implementations at large, multinational and regional banks. In addition, they actively collaborate with consumer credit modeling partners to enrich technologies and expand domain knowledge.
The SAS platform has been expanded with numerous new capabilities, including dynamic data preparation for risk modeling that enables variable sharing, complex derivation logic, and extract, transform, and load (ETL) processing, exchange and relocation. It provides a tailor-made 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 has brought stress testing to the fore and put an emphasis on assessing the impact on portfolios using a range of scenarios. This has transformed a compliance exercise into an essential management tool. In answer, SAS has developed a scenario impact simulator to help banks better facilitate the prediction of different stress scenarios through interactive analysis.
As the demand for more and better models grows, companies are looking for more flexibility to change models and policies and automate parts of the risk model lifecycle. Among other possibilities, SAS provides overlay models to support pre-pandemic models and policies, as well as new capabilities to capture and use transaction data. Another key response was to develop a risk modeling accelerator to help customers conduct analysis and test models to understand the economic impact of the pandemic.
The judges said:
- “Excellent entry and a very comprehensive and innovative response to the pandemic.”
- “It’s good to see that the focus is on easy and fast model implementation and on natural language understandability.”
- “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 Modeling and Decisioning at SASsaid:
“We are delighted to have won this award for our consumer credit modeling solution, which reflects: SASunparalleled expertise in this field. We continue to build on our extensive experience, helping major banks with a wide range of implementations, from business decisions to accelerated model development and implementation lifecycles.”