​​Economics and Machine Learning​

[Matching Markets, Auction Designs, Incentive and Social Welfare]

(Note:     students under my supervision;  † equal contribution;  * corresponding author)​​​

 

Matching Markets​​

​

• Learning strategies in decentralized matching markets under uncertain preferences. [journal][preprint]

Xiaowu Dai and Michael Jordan. 

Journal of Machine Learning Research (JMLR), 2021. 

​

• Learning in multi-stage decentralized matching markets. [proceedings][preprint]

Xiaowu Dai and Michael Jordan. 

Advances in Neural Information Processing Systems (NeurIPS), 2021.

​

• Two-sided competing matching recommendation markets with quota and complementary preferences constraints. [proceedings][preprint][code]

Yuantong Li, Guang Cheng, and Xiaowu Dai*. 

International Conference on Machine Learning (ICML), 2024.

​

• Statistical matching markets under uncertain preferences. [pdf][code]

Yiran Huang, Hanwen Ye, Xiaowu Dai*, and Annie Qu*.

Preprint, 2026.

​​

• A statistical market-design framework for academic job markets. [pdf​][code][project website]

Ali Kaazempur-Mofrad, Xiaowu Dai*, and Xuming He.

Preprint, 2026.

 

 

Auction Designs

​​​

• Online auction design using distribution-free uncertainty quantification with applications to e-commerce. [journal][reprint​][preprint][code]

Jiale Han and Xiaowu Dai*.

Journal of the American Statistical Association (JASA), 2026.

​

• Learn then decide: A learning approach for designing data marketplaces. [journal][preprint][code]

Yingqi Gao, Wenlu Xu, Jin Zhou, Hua Zhou, Yong Chen, and Xiaowu Dai*.

Journal of the American Statistical Association (JASA), 2026.​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​

​

• A robust multi-item auction design with statistical learning. [proceedings​][preprint][code]

Jiale Han and Xiaowu Dai*. 

ICLR Workshop on AI for Mechanism Design and Strategic Decision Making, 2026.

​

• Auto-bidding under return-on-spend constraints with uncertainty quantification. [proceedings​][reprint​][preprint][code]

Jiale Han, Chun Gan, Chengcheng Zhang, Jie He, Zhangang Lin, Ching Law, and Xiaowu Dai*.

The ACM Web Conference (WWW), 2026. Selected for oral presentation.

 

 

Incentives and Social Welfare

​​​

• Incentive-aware recommender systems in two-sided markets. [journal][reprint][preprint][code]

Xiaowu Dai*, Wenlu Xu, Yuan Qi, and Michael Jordan.

ACM Transactions on Recommender Systems (ToRS), 2024.

​

• Dynamic online recommendation for two-sided market with Bayesian incentive compatibility. [pdf]

Yuantong Li, Guang Cheng, and Xiaowu Dai*.

Preprint, 2024.

​​

• Direct and indirect persuasion effects under directional interference. [code]

Wenlu Xu, Xiaowu Dai*, and Lin Liu.

Preprint, 2025.

​​

 

​

​

Note: I'm also interested in designing real-world matching markets. I designed Hilbert Matching [App Store] for the clothing industry. ​​​​​

​​​​​