Scotiabank Rolls Out AI-Powered Cash Flow Predictor ‘Sofia’

Sofia (which stands for “Strategic Operating Framework for Insights and Analytics”) lets Scotiabank better support clients during the pandemic.

Need to Know 

  • Canadian bank Scotiabank has rolled out Sofia, which stands for “Strategic Operating Framework for Insights and Analytics.”
  • The tool is designed to give banks a better sense of which clients will be impacted by economic uncertainty and how to serve them by predicting cash flow.
  • A number of financial institutions are launching cash flow prediction tools and exploring predictive AI technology to better serve customers digitally during the pandemic.


Scotiabank has unveiled a new AI tool to help both retail and commercial customers to “assess and predict client needs during massive volatility.” Sofia, which stands for “Strategic Operating Framework for Insights and Analytics,” was first built for internal use during the COVID-19 pandemic, but has now been rolled out nationally. 

Using “historical commercial banking information, like customer deposits and various trends from previous years along with machine learning to predict what clients might expect in the coming weeks,” Sofia was first intended to expedite the review process for managing commercial banking accounts. 

Now, in a post-pandemic world, that same technology is being used as a “cash flow prediction tool”—to assess and predict which customers will require assistance amid ongoing uncertainty. 

The rolling four-week average predicted by Sofia gives banks a better sense of which clients will be impacted by economic downturn and how best to support them. 

“It’s really intended to be a conversation starter with our customers,” said John Phillips, Scotiabank’s director & head of the Credit Solutions Group, in a blog post on the Scotiabank website. “It’s intended to provide us with insights into accounts which may be trending down so that we can get in front of it and have discussions with our customers that are informed by the data.” 

“In the past, we’ve relied on historical reporting such as financial statements from customers,” added Chris Wise, director of the National Agricultural Credit Unit at Scotiabank. “But now through the pandemic, where it’s a more dynamic economic environment, this tool really highlights those accounts that are changing so we can direct our resources to them.” 

The roll out of Sofia is just the latest in a number of AI initiatives from Scotiabank. 

In November of 2020, the Canadian bank launched a Global AI Platform that provides personalized financial advice by using machine learning to anticipate and understand customers’ needs. The platform is designed for both business use and personal needs. 

And in September, Scotiabank teamed up with NVIDIA to adopt a new-and-improved credit card application process that is driven first by AI. 

TD Bank, a Canadian-based competitor of Scotiabank, has also begun exploring AI. In an era that is now primarily digital-first, TD is using predictive AI to provide a personalized customer experience. 

Explains Tomi Poutanen, the co-founder and CEO of Layer 6 and TD’s chief AI scientist, “For us to serve [our customers], we need to be able to proactively anticipate changes and be there when they need us. We want to have those conversations as soon as possible. That’s a service a bank can provide its customers that truly serves their interests.”