( github, linkedin, Google Scholar )
I’m a statistician and have worked on survey sampling/weighting, causal inference, AI fairness, privacy, and predictive modeling.
Meta created a system to ensure ads are delivered fairly to different demographic groups, as part of its settlement with the Department of Justice (DOJ) and the Department of Housing and Urban Development (HUD). I proposed the measurement metric (shuffle distance) and the Differential Privacy (DP) mechanisms.
Rachad Alao, Miranda Bogen, Jingang Miao, Ilya Mironov, Jonathan Tannen. (2021). How Meta is working to assess fairness in relation to race in the U.S. across its products and systems. blog post.
Miao, J., & Li, Y. P. (2022). Privacy-Preserving Inference on the Ratio of Two Gaussians Using Sums. Journal of Data Science, 1-16. paper, github.
An R and Python implementation of methods for estimating subgroup means under misclassification. github
Wang, Xiaojing, Liu, Tianqi, and Miao, Jingang. (2019). A Deep Probabilistic Model for Customer Lifetime Value Prediction. arXiv:1912.07753. github, blog post by Maja Pavlovic.
Wang, Xiaojing, Miao, Jingang, and Sun, Yunting. (2019). A Python Library For Empirical Calibration. arXiv:1906.11920. github