Jay Nanduri

Main challenge for e-commerce transaction fraud prevention is that fraud patterns are rather dynamic and diverse. This paper introduces two innovative methods, fraud islands (link analysis) and multi-layer machine learning model, which can effectively tackle the challenge of detecting diverse fraud patterns. Fraud Islands are formed using link analysis to investigate the relationships between different fraudulent entities and to uncover the hidden complex fraud patterns through the formed… Show more

Main challenge for e-commerce transaction fraud prevention is that fraud patterns are rather dynamic and diverse. This paper introduces two innovative methods, fraud islands (link analysis) and multi-layer machine learning model, which can effectively tackle the challenge of detecting diverse fraud patterns. Fraud Islands are formed using link analysis to investigate the relationships between different fraudulent entities and to uncover the hidden complex fraud patterns through the formed network. Multi-layer model is used to deal with the largely diverse nature of fraud patterns. Currently, the fraud labels are determined through different channels which are banks’ declination decision, manual review agents’ rejection decisions, banks’ fraud alert and customers’ chargeback requests. It can be reasonably assumed that different fraud patterns could be caught though different fraud risk prevention forces (i.e. bank, manual review team and fraud machine learning model). The experiments showed that by integrating few different machine learning models which were trained using different types of fraud labels, the accuracy of fraud decisions can be significantly improved. Show less

Many merchants conduct their businesses through e-commerce. One major challenge in tackling e-commerce fraud results from dynamic fraud patterns, which can degrade the detection power of risk models and can lead to them failing to detect fraud that has emerging unrecognized patterns. The problem is further exacerbated by the conventional decision frameworks that ignore the follow-up decisions made by other associated parties (e.g., payment-instrument-issuing banks and manual review agents)… Show more

Many merchants conduct their businesses through e-commerce. One major challenge in tackling e-commerce fraud results from dynamic fraud patterns, which can degrade the detection power of risk models and can lead to them failing to detect fraud that has emerging unrecognized patterns. The problem is further exacerbated by the conventional decision frameworks that ignore the follow-up decisions made by other associated parties (e.g., payment-instrument-issuing banks and manual review agents). Microsoft developed a new fraud-management system (FMS) that effectively tackles these two challenges. It keeps features used by the machine learning (ML) risk models up to date by using real-time archiving, dynamic risk tables, and knowledge graphs. The FMS uses customized long-term and short-term sequential ML models to detect both historical and emerging fraud patterns. It also makes rapid real-time optimal decisions using a dynamic programming approach to optimize the long-term profit by taking into account the aforementioned multiple-party decisions. After implementing these innovations over a two-year period (2016–2018), Microsoft reduced its fraud loss by 0.52%, thus generating $75 million in additional savings; reduced the incorrect fraud rejection rate by 1.38%; and improved its bank authorization rate by 7.7 percentage points. The result was many millions of dollars in additional revenue. These innovations simultaneously prevent fraud and increase bank acceptance. In April 2019, Microsoft launched Microsoft Dynamics 365 Fraud Protection, a cloud-based service available for all e-commerce merchants. Show less

This podcast is part of a series highlighting the finalist teams of the 2019 INFORMS Franz Edelman Award. We will be releasing these episodes in the countdown to the INFORMS Business Analytics Conference in Austin, TX, April 14-16. In this episode, we are joined by Jay Nanduri, Distinguished Engineer, and Anand Oka, Principal Group Program Manager with Microsoft to learn how Microsoft leveraged O.R. to create a fraud detection system that identifies and reduces online fraudulent activity, while… Show more

This podcast is part of a series highlighting the finalist teams of the 2019 INFORMS Franz Edelman Award. We will be releasing these episodes in the countdown to the INFORMS Business Analytics Conference in Austin, TX, April 14-16. In this episode, we are joined by Jay Nanduri, Distinguished Engineer, and Anand Oka, Principal Group Program Manager with Microsoft to learn how Microsoft leveraged O.R. to create a fraud detection system that identifies and reduces online fraudulent activity, while protecting legitimate consumer purchases and saving tens of millions of dollars. Show less