Data Labeling and ML Modeling Engineer (Financial Loan Default Risk Analysis)
In the 金融风控-贷款违约预测分析项目, I led the data gathering and curation of financial datasets for use in machine learning credit risk models. My responsibilities included web data scraping, cleansing, and labeling features relevant to loan default risk. I performed model development, feature engineering, and validation for optimal predictive accuracy. • Labeled financial risk features from raw web-scraped datasets. • Designed entity and feature classification schemes for machine learning use. • Visualized and validated feature sets for downstream modeling with Python tools. • Deployed results on a web platform for team and client access.