We solve critical and challenging business and societal problems by designing novel and rigorous machine learning algorithms and methods, rather than applying existing ones. A typical research project begins by identifying a significant business or societal problem and analyzing its unique characteristics that cannot be effectively addressed by existing machine learning algorithms. Based on this analysis, a novel machine learning algorithm or method is developed to tackle these challenges, thereby solving the problem effectively and efficiently. In our research, we strive to make methodological contributions to both Information Systems and machine learning. This stream of research is known as the Computational Design Science research in the Information Systems field. More broadly, it belongs to the Use-Inspired AI research, as defined by the National Science Foundation. Specifically, our research projects seek to maximize AI’s Benefits for business and society while minimizing its potential Harms.
Detecting LLM-generated Content (H)
Mao, M., Wei, D., Fang, X., Chau, M. 2025. A General Method for Detecting Information Generated by Large Language Models.
Mao, M., Wei, D., Chen, Z., Fang, X., Chau, M. Watermarking Large Language Models: An Unbiased and Low-risk Method. Association for Computational Linguistics (ACL), 2025.
Debiasing LLM (H)
Fang, X.*, Che, S.*, Mao, M., Zhang, H., Zhao, M., Zhao, X. 2024. Bias of AI-Generated Content: An Examination of News Produced by Large Language Models. Scientific Reports, 14:5224.
Chen, S., Mao, M., Zhao, M., Fang, X. 2025. Debiasing Large Language Models: A Novel Approach to Mitigating Demographic Bias.
LLM for Business and Social Good (B)
Che. S., Mao, M., Liu, H., Fang, X. 2025. New community cold-start recommendation: A novel large language model-based method.
Yin, B., Zhu, Y., Mao, M., Zhang, H., Fang, X. 2025. Boosting LLM-Based Credit Risk Prediction via Graph-Driven Multiview Representations: A Fine-Tuning-Free Approach.
FinTech: Financial Document Analytics (B)
Zhao, X., Fang, X., He, J., Huang, L. 2023. Exploiting Expert Knowledge for Assigning Firms to Industries: A Novel Deep Learning Method. MIS Quarterly, 47 (3), pp.1147-1176.
Zhao, X., Fang, X., He, J., Sheng, O. 2025. A Novel Document Embedding Approach to Industry Classification.
FinTech: Credit Risk Modeling (B)
Zhang, H., Qian, W., Fang, X. 2025. Latent Similarity-Enhanced Credit Risk Prediction. Accepted by MIS Quarterly.
Zhang, H., Fang, X. 2025. Privacy-Preserving Credit Risk Prediction with Alternative Data.
Misinformation Detection (H)
Mao, M., Zhao, X., Fang, X. 2025. Early Detection of Misinformation for Infodemic Management: A Domain Adaptation Approach.
Mao, M., Wei, D., Fang, X., Chau, M. 2025. A General Method for Detecting Information Generated by Large Language Models.
Information Privacy (H)
Han, X., Wang, L., Wu, J., Fang, X. 2025. Data Valuation for Vertical Federated Learning: A Model-free and Privacy-preserving Method. Accepted by MIS Quarterly.
Zhang, H., Fang, X. 2025. Privacy-Preserving Credit Risk Prediction with Alternative Data.
Social Network Analytics (B)
Li, Z.*, Fang, X.*, Bai, X. and O. R. Liu Sheng. 2017. Utility-based Link Recommendation for Online Social Networks. Management Science, 63 (6), pp. 1938-1952. (*Equal contribution).
Yin, K., Fang, X., Chen, B., Sheng, O. 2023. Diversity Preference-aware Link Recommendation for Online Social Networks. Information Systems Research, 34 (4), pp. 1398-1414.
Healthcare Analytics (B)
Fang, X., Gao, Y., and Hu, P. 2021. A Prescriptive Analytics Method for Cost Reduction in Clinical Decision Making. MIS Quarterly, 45 (1), pp. 83-115.
Xie, J.*, Zhao, X.*, Liu, X., Fang, X. 2025. Care for the Mind Amid Chronic Diseases: An Interpretable AI Approach Using IoT. Accepted by Management Science.
Space