I am a Ph.D. candidate in the Computer Science Department, Cornell University and Cornell Tech. I am very fortunate to be advised by Prof. Deborah Estrin, and be a member of the small data lab and the Connected Experiences lab (Cx lab).

    I am driven to build intelligent information systems (e.g., recommender systems, personal assistants, and their applications, from education to wellness) that address individual, commercial, and societal needs, and to understand limitations and real-world impacts of algorithmic suggestions. I push the boundaries of these systems by

    developing novel computational methods and algorithms for behavioral modeling,
    analyzing large-scale and counterfactual behavioral data, and
    implementing and deploying systems for lab and field experiments.
    My previous research addressed content recommendation systems. I designed and built a class of user-centric recommendation systems focusing on people’s needs and utility — I built systems that profile users across platform boundaries [WWW 16][WWW 17a], guide users toward more healthy diets [CIKM 15][TOIS 17], and encourage exploration beyond narrow information channels [WWW 19]. In addition, my work revealed impacts and fundamental limitations of recommendations from a user’s perspective — I addressed bias in recommender evaluation [Recsys 18a], discovered nuanced user preferences overlooked by recommenders [WSDM 19], and demonstrated how recommendations modulate users’ choices [Recsys 18b] [WWW 19]. I built, released, and maintain an open-source framework for reproducible and extensible recommendation research and engineering [WSDM 18].