I am an Assistant Research Professor at the Center for Data Science for Enterprise and Society (CDSES) at Cornell University. My research focuses on the interplay between data, algorithms, and markets. More precisely, I am interested in designing algorithms for learning and optimization problems in online marketplaces, such as pricing, advertising and a/b testing.
A large bulk of of my work are motivated by collaboration with industry. For example, we collaborated with Glance, India's largest mobile lock-screen content platform, to improve their recommender system for short-lived contents, and showed the effectiveness of our policy in a large-scale field experiment.
Prior to joining Cornell, I obtained my PhD degree in the ACO program (Algorithms, Combinatorics and Optimization) at the Tepper School of Business, Carnegie Mellon University. I was fortunate to be able to work with R. Ravi and Andrew Li. I received my BS degree in Mathematics from Tsinghua University in 2014, and MS degree in Applied Mathematics and Statistics from the State University of New York at Stony Brook in 2017, where I was fortunate to work on computational geometry with Joseph Mitchell and Jie Gao.
I received the INFORMS Pierskalla Best Paper Award in Health Applications in 2021. I have also been selected as a finalist for the INFORMS Dantzig Dissertation Award in Management Science in 2022. Here is my CV.
Su Jia, Nishant Oli, Andrew Li, R. Ravi, Paul Duff, Ian Anderson.
Platforms have been leveraging the scale of data to build recommenders for newly-generated contents. Drawing ideas from bandit theory, we propose policies for recommending a high-volume of short-lived contents, which we also show to be nearly best possible theoretically. More importantly, we collaborated with Glance, India's largest lockscreen content company and implmented a large-scale field experiment on their real system, where our policy significantly outperformed their current DNN-based recommender.
Su Jia, Andrew Li, R. Ravi (NeurIPS'22)
Our previous work showed the first separation between markdown and unconstrained pricing, under minimal assumptions. However, in practice, demand functions are usually assumed to have certain functional forms, which can potentially be utilized for designing better policies. We introduce a notion called "markdown dimension" that measures the difficulty of performing markdown pricing on a family, and provide a complete settlement of the problem by proving a tight regret bound for each markdown dimension.
Kyra Gan, Su Jia, Andrew Li, Sridhar Tayur. (NeurIPS'21) Winner, INFORMS Pierskalla Best Paper Award 2021
Liquid biopsy is an emerging approach for early cancer detection, which aims at detecting mutations from the free-floating DNA in the blood. We consider the Active Hypothesis Testing problem, where the goal is to identify the unknown cancer type using minimal number of tests. In addition to theoretical guarantees, we also demonstrated the practical efficacy of our policies on real DNA mutation data.
Su Jia, Jeremy Karp, R. Ravi, Sridhar Tayur. (Manufacturing and Service Operations Management)
Retailers nowadays may use in-store inventory to fulfill the demands from different channels. As opposed to the offline channel, the online channel is more flexible and its orders are fulfilled only periodically. The key problem then is how to jointly manage the orders from these two channels, with consideration of both profit and fulfillment level. We propose a gradient-based computational framework for finding the optimal threshold policy, and demonstrate its effectiveness using Onera's data.
Su Jia, Andrew Li and R.Ravi. (Major Revision, Management Science), Egon Balas Award for best CMU student OR paper
Dynamic pricing with unknown demand has been extensively studied and often formulated as a bandit problem. While well-understood theoretically, bandit-based policies are rarely deployed in the real world, largely due to overlooking practical constraints. For example, the price may oscillate, which is unfavorable in practice. We consider markdown policies, i.e. policies with non-increasing prices, and show a tight regret bound that "separates" markdown and unconstrained pricing under unknown demand.
Su Jia, Fatemeh Navidi, Viswanath Nagarajan and R.Ravi. (NeurIPS'19)
In medical diagnosis, a sequence of medical tests is performed to identify the patient's disease. The problem of finding the lowest cost testing procedure (i.e. decision tree) for a given set of tests is a classical problem in discrete optimization. As opposed to prior work where the test outcomes are assumed to be known, we consider the setting where some tests may have unknown outcomes, and provide the first approximation algorithms.