Wei Sun (IBM T. J. Watson Research Center) – Counterfactual-based Prescriptive Trees

In this talk, we will present a framework on prescriptive analytics that has been successfully applied to several clients’ projects including a major US airline and a large financial institution. The framework consists of a causal teacher model which produces counterfactual outcomes corresponding to different treatment actions, and a prescriptive student model which distills a set of policies that optimizes a given objective in the form of a tree. The prescriptive tree can be built greedily as demonstrated in our ICML 2021 paper. As the greedy heuristic is unable to incorporate constraints that are ubiquitous, in our AAAI 2022 publication, we introduce a scalable mixed-integer program (MIP) approach that solves the constrained prescriptive policy generation problem via column generation.

Papers related to the talk:
Model Distillation for Revenue Optimization: Interpretable Personalized Pricing
https://proceedings.mlr.press/v139/biggs21a.html
Constrained Prescriptive Trees via Column Generation
https://www.aaai.org/AAAI22Papers/AAAI-12523.SubramanianS.pdf

Wei Sun is a Senior Research Scientist at the AI Marketing Group under Services Research division of IBM T. J. Watson Research Center in Yorktown Heights, NY. She is also a research affiliate with MIT Sloan School of Management. Her research centers on the intersections of machine learning and optimization, including prescriptive analytics, constrained prediction, counterfactual inference, and reinforcement learning. Wei graduated with a Ph.D. in Operations Research and a M.S. in Computational Design and Optimization from MIT, and a B.Eng. in Electrical and Computer Engineering from the National University of Singapore.

For more information about the ESD Seminar, please email esd_invite@sutd.edu.sg