Predictive analytics is a branch of data science that applies various techniques, including statistical inference, machine learning, data mining, and information visualization, toward the ultimate goal of forecasting, modeling, and understanding the future behavior of a system based on historical and/or real-time data. Predictive analytics has only recently seen interest or adoption in risk management, which has the potential to be widely applied to determine business events that are likely to occur and be actionable.

Our research team focuses on data-driven modeling techniques, and topics of particular interest include but are not limited to:

Statistical learning algorithms for loss modeling, fraud detection, etc.
AI-Powered lifecycle financial planning
Cyber risk data analytics
Automated Machine Learning (AutoML) for imbalanced datasets
Tree-based models with modified loss functions
Large-scale parallel computing