RANCHO CUCAMONGA, Calif.–CO-OP Financial Services has offered an update on how it is using artificial intelligence to fight fraud, including a machine learning-based, risk-management tool to be utilized by CO-OP for its client credit unions in 2017.
As CUToday.info reported earlier here, the company has also been using artificial intelligence to fight false positives on card transactions.
“A key pain point for credit unions in 2017 is that fraud mitigation tools have not kept pace with the relentless advance of fraud,” said Todd Clark, president/CEO of CO-OP. “CO-OP Financial Services has an equally relentless commitment to credit union and cardholder security. We are investing $20 million this year on new innovations to ensure credit unions have access to the very best technology in the payments industry. Implementing machine learning capabilities is a key initiative in delivery on that promise.”
CO-OP said it has partnered with San Mateo, Calif.-based Feedzai, which specializes in artificial intelligence for payments applications, to develop solutions to address fraud at any transaction volume. Machine learning is a key component of AI allowing machines to automatically learn from data and adapt, with or without human supervision, the company noted.
“To be used exclusively on behalf of CO-OP-client credit unions, the agile machine learning platform will work in real-time, incorporate advanced analytics and provide alert and case management capabilities for fraud and risk services,” CO-OP said.
For card payments, machine learning will augment the existing neural network-based Falcon Fraud Manager fraud detection system used by the CO-OP Card Member Security Team, the company added. “Feeding on historical and current data, the platform will utilize a strengthened transaction scoring model to better predict debit and credit card fraud, reducing credit unions’ losses while keeping false alarms to a minimum.”
In addition, machine learning will be deployed as the primary fraud management tool for CO-OP Shared Branching.
According to CO-OP, the platform will be able to take in any amount of relevant, multi-source data to define transaction risk scoring, incorporating events such as cardholder PIN changes and the purchasing patterns of individual members to better predict expected behavior. Based on constant learning and scoring updated in real-time, suspect transactions detected by machine learning can be declined on the spot or kicked out immediately to fraud team members for analysis, CO-OP said.
“The CO-OP-Feedzai partnership is structured for the co-development of a series of fraud-fighting, machine learning advances beyond the risk management tool to be utilized by CO-OP later this year,” the company said. “It is also part of a three-pronged security strategy that includes fraud consulting and tools such as CardNav by CO-OP, a card controls and alerts application that helps empower members in their own defense against fraud.”