Summary
Chase Ji is a data scientist based in Beijing with 11 years of experience applying statistical and machine learning techniques to large-scale, real-world problems. With an MS in Financial/Applied Mathematics from Johns Hopkins and a BS in Mathematics and Economics from UVA, he has built end-to-end predictive systems—from petabyte-scale preprocessing and feature engineering to model validation and deployment—across domains like insurance fraud detection and credit risk. At Distilled Identity he engineered time-series feature extraction and spatial-temporal aggregations across billions of records, and at DiDi focused on anti-fraud systems before joining Kuaishou to work on product-scale ML. He favors Python-driven, reproducible codebases and practical approaches (XGBoost, SMOTE, Spark, TSFresh) that deliver measurable business impact, including substantial cost savings in fraud investigations. Known for digging into the data-generating process, he combines rigorous quantitative training with hands-on engineering to turn messy data into actionable models.
11 years of coding experience
2 years of employment as a software developer
Master of Science - MS, Financial Mathematics, 3.6/4.0, Master of Science - MS, Financial Mathematics, 3.6/4.0 at Johns Hopkins Whiting School of Engineering
Bachelor of Science - BS, Mathematics, Economics. Minor in Statistics., Bachelor of Science - BS, Mathematics, Economics. Minor in Statistics. at University of Virginia