His research activities have ranged from applications of reinforcement learning to business analytics, methods for anomaly detection, temporal causal modeling, cost-sensitive learning and on-line active learning, among other topics. Methodologies that he co-developed through these research efforts have made their ways into a number of IBM offerings, including Temporal Causal Modeling engine in SPSS Modeler and Statistics, Granger anomaly detection engine in Smart Cloud Predictive Insights, the Tax Collections Optimizer and Signature Solutions “Next Best Action” and “CFO-dashboard.”