Wei Sun

I am a Senior Research Scientist at IBM Research in Yorktown Heights, NY. I am part of MIT-IBM AI Lab, under AI Data Model Factory. I am also a research affiliate at MIT Sloan School of Management. My research centers on the intersections of machine learning and optimization, with topics including AI-driven decision-making, constrained predictive models, causal inference, and game theory. My work has been applied to solve real-world challenges of many companies in digital marketing, travel/transport, and financial services. 

I graduated with a Ph.D. in Operations Research from MIT, and an M.S. in Computational Design and Optimization from the same school. My dissertation advisor was Georgia Perakis. I also have an M.S. in Computational Engineering, and a B.Eng. in Electrical and Computer Engineering with First-Class Honors from National University of Singapore.

News & Highlights

• I gave a tutorial on Combining LLMs and OR/MS to Make Smarter Decisions at the INFORMS Annual Meeting in October 2024
• I was invited to Dagstuhl Seminar on Leveraging AI for Management Decision-Making in August 2024
• Project Interpretable Policy Learning Utilizing Counterfactuals, in which I am the technical lead, won 3rd place at INFORMS Innovative Applications in Analytics Award 2024. In this client engagement, we implemented the framework proposed in our paper and observed a 7% revenue gain during a four-month live deployment, resulted in client adoption with a broad market rollout
• I gave a talk at MIT Operations Research Center, part of OR Through the Ages seminar series in January 2024

Recent Work

Combining Large Language Models and OR/MS to Make Smarter Decisions Segev Wasserkrug, Léonard Boussioux, Wei Sun. Tutorials in Operations Research: Smarter Decisions for a Better World. 2024

API Pack: A Massive Multi-Programming Language Dataset for API Call Generation Zhen Guo, Adriana Meza Soria, Wei Sun, Yikang Shen, Rameswar Panda

Domain Adaptable Prescriptive AI Agent for Enterprise Piero Orderique, Wei Sun, Kristjan Greenewald. Demo link

PresAIse, Prescriptive AI Solution for Enterprise Wei Sun, Scott McFaddin, Linh Ha Tran, Shivaram Subramanian, Kristjan Greenewald, Yeshi Tenzin, Zack Xue, Youssef Drissi, and Markus Ettl. INFOR: Information Systems and Operational Research. An earlier version was presented at AAAI Workshop on AI for OR 2024

Learning Optimal Projection for Forecast Reconciliation of Hierarchical Time Series Asterios Tsiourvas, Wei Sun, Georgia Perakis, Pin-Yu Chen, Yada Zhu. ICML 2024

Manifold-Aligned Counterfactual Explanations for Neural Networks Asterios Tsiourvas, Wei Sun, Georgia Perakis. AISTATS 2024

Learning Prescriptive ReLU Networks Wei Sun, Asterios Tsiourvas. ICML 2023

Scalable Optimal Multiway-Split Decision Trees with Constraints Shivaram Subramanian*, Wei Sun*. AAAI 2023 (*: Equal contribution)

Tiered Assortment: Optimization and Online Learning Junyu Cao, Wei Sun. Management Science 2023

Enhancing Counterfactual Classification via Self-Training Ruijiang Gao, Max Biggs, Wei Sun, Ligong Han. AAAI 2022

Constrained Prescriptive Trees via Column Generation Shivaram Subramanian*, Wei Sun*, Youssef Drissi, Markus Ettl. AAAI 2022 (*: Equal contribution)

Model Distillation for Revenue Optimization: Interpretable Personalized Pricing Max Biggs, Wei Sun, Markus Ettl. ICML 2021

Fatigue-aware Bandits for Dependent Click Models Junyu Cao, Wei Sun, Max Shen, Markus Ettl. AAAI 2020

Strategic Capacity Planning Problems in Revenue‐Sharing Joint Ventures Retsef Levi, Georgia Perakis, Cong Shi, Wei Sun. Production and Operations Management 2020

Dynamic Learning of Sequential Choice Bandit Problem under Marketing Fatigue Junyu Cao, Wei Sun. AAAI 2019

Dynamic Learning with Frequent New Product Launches: A Sequential Multinomial Logit Bandit Problem Junyu Cao, Wei Sun. ICML 2019