Download Image

Pan Li

Assistant Professor

pan.li@scheller.gatech.edu

Download VITA

Personal Website

Google Scholar

Academic Areas: IT Management

Suite: 496

Office: 4161

Biography

Pan Li is an Assistant Professor of Information Technology Management in the Scheller College of Business at Georgia Institute of Technology. His research focuses on personalization techniques, where I aim to improve the design of recommendation models that effectively explore consumer preferences and improve consumer satisfaction.

The results of his work were published in 12 journal and conference papers, and some of his proposed methods were implemented by leading tech companies, including Alibaba and Baidu. He has won the Best Dissertation award and the Best Student Paper Runner-Up award at the WITS 2021 Conference, and has been invited to present his research at the doctoral consortia of WSDM, RecSys and WITS conferences.

Education

Ph.D., New York University Stern School of Business, 2023
M.S., New York University Stern School of Business, 2021
B.S., University of Science and Technology of China, 2017

Teaching Interests

Professor Pan Li is the instructor for MGT-6213 Business Analytics for Managers and MGT-4050 Business Analytics. He designed the class with the goal of providing the students, who came from both technical and business backgrounds, with a comprehensive introduction to the recent developments in AI through the coverage of fundamental machine learning & deep learning concepts and practical applications of these concepts in business. In the class, they learned how to apply business analytics methods for solving practical business problems and also learned where the AI technologies would be heading within the next few years.

Research Interests

Professor Pan Li’s research focuses on developing novel personalization methods, especially recommender systems, that are grounded in well-established consumer behavior theories, such as variety-seeking and multi-channel marketing, to improve performance in various business applications and bring in significant economic benefits. Specifically, he focuses on the following four major research streams: (1) Consumer Preference Exploration in Recommender Systems; (2) Cross-Domain Recommender Systems; (3) Multi-Objective Recommender Systems; and (4) Interpretable Machine Learning. Beyond these research streams, he has also worked on various projects related to Natural Language Processing and Machine Learning, such as automated generation of consumer reviews based on their sentiment and stylistic information. Overall, his research spans the boundaries of Information Systems and AI/Machine Learning disciplines, and has led to multiple publications in Information System Research, MIS Quarterly, and IEEE Transactions on Knowledge and Data Engineering (TKDE).

Research Publications

Show Citations

Filter By:

Year

Type

Year	Title	Journal	Author(s)	Type
2024	When Variety-Seeking Meets Unexpectedness: Incorporating Variety-Seeking Behavior into Design of Unexpected Recommender Systems	Information System Research (ISR)	Pan Li Alexander Tuzhilin	Published Papers	View
Pan Li, Alexander Tuzhilin, “When Variety-Seeking Meets Unexpectedness: Incorporating Variety-Seeking Behavior into Design of Unexpected Recommender Systems”, Information System Research (ISR) Volume: 35 Issue: 3, pp.1257-1273. (2024)
2024	Dual Contrastive Learning for Efficient Static Feature Representation in Recommender System	IEEE Transactions on Knowledge and Data Engineering (TKDE)	Pan Li Maofei Que Alexander Tuzhilin	Published Papers	View
Pan Li, Maofei Que, Alexander Tuzhilin, “Dual Contrastive Learning for Efficient Static Feature Representation in Recommender System”, IEEE Transactions on Knowledge and Data Engineering (TKDE) Volume: 36 Issue: 2, pp. 544-555 (2024)
2023	Dual Metric Learning for Effective and Efficient Cross-Domain Recommendations	IEEE Transactions on Knowledge and Data Engineering (TKDE)	Pan Li Alexander Tuzhilin	Published Papers	View
Pan Li, Alexander Tuzhilin, “Dual Metric Learning for Effective and Efficient Cross-Domain Recommendations”, IEEE Transactions on Knowledge and Data Engineering (TKDE) Volume: 35 Issue: 1, pp. 321 - 334 (2023)
2023	Reconstructing Universal Embeddings of Customers from Domain-Specific Embeddings	ACM Transactions on Management Information Systems (TMIS)	Moshe Unger Pan Li Shahana Sen Alexander Tuzhilin	Published Papers	View
Moshe Unger, Pan Li, Shahana Sen, Alexander Tuzhilin, “Reconstructing Universal Embeddings of Customers from Domain-Specific Embeddings”, ACM Transactions on Management Information Systems (TMIS) Volume 14, Issue 2, Article No. 20, pp 1–30 (2023)
2022	Adversarial Learning for Cross-Domain Recommendations	ACM Transactions on Intelligent Systems and Technology (TIST)	Pan Li Brian Brost Alexander Tuzhilin	Published Papers	View
Pan Li, Brian Brost, Alexander Tuzhilin, “Adversarial Learning for Cross-Domain Recommendations”, ACM Transactions on Intelligent Systems and Technology (TIST) Volume 14, Issue 1, Article No. 5, pp 1–25 (2022)
2022	Learning Latent Multi-Criteria Ratings from User Reviews for Recommendations	IEEE Transactions on Knowledge and Data Engineering (TKDE)	Pan Li Alexander Tuzhilin	Published Papers	View
Pan Li, Alexander Tuzhilin, “Learning Latent Multi-Criteria Ratings from User Reviews for Recommendations” , IEEE Transactions on Knowledge and Data Engineering (TKDE), Volume: 34 Issue: 8, pp. 3854 - 3866 (2022)

Showing of 6