I am a data scientist at Beth Israel Deaconess Medical Center in Boston, MA. I am interested in using data and algorithm to solve real-life problems in various fields, including healthcare and marketing.

Gem-T
A synthetic data generator for tabular datasets and time series: read more

Data quality for computer vision
Similarity-inspired approach to define data quality: read more

Healthcare

• High Risk Pregnancy in Mississippi Delta: Predicting high-risk pregnancy with survey data (logistic regression, GBM, random forest)
• CappyDoctor: Predicitng Pneumonia from X-Ray images (computer vision)

Marketing

• Digital Market Analysis for Red Wine in US: Leveraging NLP and marketing algorithms to draw insight from red wine market using Wine Enthusiast and Vivino Data (Sentiment Analysis, Aggregated Conjoint Analysis)
• News page for Harris School of Public Policy: Scraping news and podcast related to Harris School of Public Policy and use NLP to detect policy topics (web scraper, NLP)

Others

• Project with Chicago Metropolitan Agency for Planning: Built automatic model optimization and evaluation pipline with Wandb
• AI's impact on employment landscape: Using NLP to explore how AI is impacting job market and extracting actionable recommendations from 200k unstructured new articles
• CappyFoodies: Food accessibility and Yelp review for restaurants in Cook County, IL (data visualization, interactive dashboard)