Improved accuracy in fraud detection in financial transactions using deep learning and generative AI techniques
Improve Fraud identification in banking transactions
Existing rules driven System was very cumbersome to maintain and customer was not able to keep up with new kinds of suspicious activity that was continuously evolving.
Machine Learning System that ingested millions of customer transactions over a 3-year time-period was used to analyze the suspicious activity. A combination of Graph GAN + NEAT was used to build a predictive model for suspicious activities.
Analyzes every transaction for suspicious activity and flags suspicious behavior at near real time and integrates with all downstream workflow elements to resolve the activity.