Artificial intelligence for good: Using AI to stop fraud and scams in financial services
“On Wednesday, May 7 the Center on Regulation and Markets at the Brookings Institution convened a panel of leading experts from Block, JP Morgan Chase, and FinRegLab to discuss the potential for AI as a new weapon to fight fraud and scams.”
AI-powered banking fraud on the rise – but financial institutions are fighting back
“Financial institutions are fighting back by using AI themselves. Nine in ten are already using AI to detect fraud, and two-thirds have integrated AI within the past two years. Meanwhile, 90% of financial institutions are attempting to prevent fraud with AI-powered solutions. And it’s working, with four in ten saying that AI had helped them cut fraud losses by between 40% and 60%, and 43% that it had led to a 40-60% improvement in efficiency.”
AI fraud detection in banking
“Since implementation, various financial institutions and banks have found significant evidence to support the increasing adoption of AI fraud detection. Using advanced, long short-term memory (LSTM) AI models, American Express was able to improve fraud detection by 6%. And PayPal was able to improve their real-time fraud detection by 10% through AI systems running around the clock, worldwide.”
Oscilar Launches AI-Powered ACH Fraud Detection for FinTechs, Financial Institutions
“The solution addresses several types of fraud, including first-party fraud, account takeover, stolen account details, scams, business email compromise (BEC), money mules and ACH check kiting, according to the release. Its fraud detection capabilities analyze bank account usage patterns and validate intent, detect new attack vectors, and help risk operations teams scale their investigations and reviews, the release said.”
AI Applications In Fraud Detection In The Banking Industry
“• JPMorgan Chase: JPMorgan Chase enhanced its fraud detection by integrating large language models (LLMs) to analyze transaction patterns in real time. This AI-driven system reduced fraud-related losses by 40% and improved detection speed. By prioritizing explainability and a phased rollout alongside legacy systems, JPMorgan set a new benchmark for adaptive, AI-powered fraud prevention in banking.”
Beyond detection: An AI-powered approach to proactive fraud prevention
“To effectively combat fraud, FIs must adopt a customer-centric and holistic approach to risk decisioning. Fraudulent activity does not cease at the application stage – ongoing monitoring and analysis of customer behaviour are crucial for detecting emerging fraud threats throughout the entire customer lifecycle, from initial application to high-risk event monitoring.
Newly opened accounts typically exhibit a higher risk of fraudulent activity. Therefore, re-utilizing application data or re-screening high-risk events to identify anomalous behaviour is essential. For instance, how frequently would a legitimate customer alter their address, phone number, or device immediately after account opening?”