Reported by: banking|Updated: May 30, 2019
Housing finance companies are now making use of Big Data in risk management and fraud detection and prevention. A recent report in Banking Frontiers discusses how Big Data is helping them in these 2 areas. Manish Jaiswal, MD and CEO, Magma Housing Finance says that Big Data powered by machine learning and artificial intelligence will increase the efficiency of underwriting, fraud risk, collection risk etc. Cloud computing will merely provide unrestricted flexibility and ease of access to required information, he adds. Says Jaiswal: “Traditionally HFCs have used bureau data, demographic and internal behavior to develop strategies for sourcing, underwriting and customer life cycle management. However, it seems pertinent that the digital footprints through different sources and online validation tool data will also need to be analyzed for performing better checks, better services and better controls.”
According to Nafees Ahmed, CIO at Indiabulls Goup, fraud possibilities co-evolve with technology, especially information technology and often business re-engineering, reorganization or downsizing may weaken or eliminate control, while new information systems may present additional opportunities to commit fraud. “Fraud,” he says, “is an adaptive crime, so it needs special methods of intelligent data analysis to detect and prevent. These methods exist in the areas of Knowledge Discovery in Databases (KDD), Data Mining, Machine Learning and Statistics.”
Deo Shankar Tripathi, MD & CEO at Aadhar Housing Finance, thinks risk management practices need to evolve further to put the usage of Big Data into traditional practice.
Jaiswal mentions that methodologies involving analytics have been developed for fraud detection. He avers it is behavioral science that plays a major role here. For him, the methodologies are mostly on the inconsistencies in data submission, alerts basis rules derived through analytics and other behavioral mismatches.
“Unfortunately, fraud is a billion-dollar business and it is increasing every day,” says Nafees Ahmed, adding: “Detecting and preventing fraud is not a simple task, so it needs special methods of intelligent data analysis. There are 2 techniques currently in use – statistical analysis and artificial intelligence.”