Did You Miss These Learnings from Enova Decisions at CFCA 2019?

Right in the middle of a broiling summer, it’s hard to believe Enova Decision’s sponsorship at the 2019 Annual Meeting & Educational Event for CFCA has come and gone. While we all look forward to next year’s CFCA, we want to make sure you didn’t miss out on some of the key trends we discussed at this year’s event.

We were there to demonstrate how the latest Enova Decisions Cloud can reduce application fraud vulnerabilities for communications carriers, service providers, and their partners. But in addition, one of the key presentations was a talk by Sean Naismith, GM & Head of Analytics Services at Enova Decisions, entitled “Lessons from FIs on Application Fraud Detection.” Whether you were able to attend, here are just a few of Sean’s “lessons learned” you may have missed:

  • Successful fraud detection requires nonlinear and nonparametric modeling
  • Automated, continuous retraining of the models will ensure their predictive power
  • In addition, major redesign of models should be performed annually

Sean also discussed other lessons Enova Decisions has learned through long experience, including velocity variables, link variables, 3rd-party data integrations, and more. All these lessons—plus the ease-of-use, machine learning, and AI in our cloud-based real-time decision management software-as-a-service—allow us to help our customers revamp their organization’s fraud prevention strategies for today’s challenges.

So, if you missed Sean’s presentation—or if you’d like a refresher—contact us for a copy of the slide deck and to schedule a time so we can walk you through it.

Contact us now to get your copy of “Lessons from FIs on Application Fraud Detection.”

Enova Decisions


Enova Decisions is an analytics and decision management technology company that was formed in 2016 to enable businesses in various industries, including financial services, healthcare, and telecommunications, to automate and optimize operational decisions, in real-time and at scale, through data, machine learning, and the cloud.