Creating Effective Revenue Forecast Models for CCAR using Machine Intelligence

05.05.2022 | By Mark Speyers

The recent webinar entitled Creating Effective Revenue Forecast Models for CCAR using Machine Intelligence discusses the brief history of the Federal Reserve’s annual stress test and how it has fundamentally changed over the last seven years.

One of our previous posts explains the birth of CCAR and how market conditions created the necessity of a liquidity framework aimed to evaluate key bank’s earnings under various stress scenarios.

As the economy has bettered since the crash in 08, the fed’s concerns have shifted from the bank’s monetary stability to questions addressing the soundness of their risk management practices.’s webinar offers viewpoints from banks of different caliber. Lourenco Miranda, Managing Director of Operations Risk Quantification, Capital and CCAR at AIG, offers a bigger-bank’s perspective of the CCAR process. Kenneth Swenson, Senior Vice President and Manager of Operational Risk Modeling at Regions Bank discusses the mid-sized, regional bank’s processes. And our own Michael Woods speaks on Ayasdi’s efforts to help construct effective revenue forecast models.

Kenneth explains the current challenges for some of the mid-sized regional banks. In order to implement and operationalize CCAR it requires compiling data from various sources including economics, business lines, risk management, and even HR. You then have to aggregate that data to have an output that can be submitted to the feds in a timely and accurate fashion.

Lourenco discusses his key findings after having spent the last five years at top CCAR contending banks including AIG and US Bank. He explains that validation is something that modelers are paying more and more attention to. The importance of switching from the quantitative developers to the validation team is crucial in generating an effective result.

CCAR continues to evolve from not just a regulatory solvency assessment but into a method to run the bank and enhance efficiency. Banks must comply with ethical, systemically transparent, credible, and verifiable outputs which are embedding a new holistic framework for enterprise risk management.

For the full effective revenue forecast models, we encourage you to listen to the entire webinar here.


Latest Insights

convenience fuel retailing Fuel Retail Analytics
05.17.2024 Blog

Shopper Analytics Give Convenience Retailers Fuel to Increase Loyalty and In-Store Sales

Retail / CPG Square Icon Svg
Using vertical AI to solve specific business problems

Using vertical AI to solve specific business problems

AI Square Icon Svg
Introducing SensaAI for Sanctions

Introducing SensaAI for Sanctions

Financial Services Square Icon Svg