Yangyang Hong

• Implemented feature system in Java that supports incremental updates and time tracking for both recommender system and search engine, reducing the time to generate features by 25%.
• Enhanced end-to-end recommender system by employing advanced techniques (DeepFM, hash embedding) and fine-tuning, resulting in 4.3% increase in click-through rate, up from previous 3.5%.
• Built sophisticated search engine by integrating Elasticsearch-powered matching, relevance model, and ranking via DeepFM model, leading to 4% increase in click-through rate, up from previous 76.5%.
• Supported framework to deploy both recommender system and search engine in fully configurable manner across 9 markets.

Data Scientist, 01/2020 - 12/2021

• Built a repurchase prediction model using lightGBM with an AUC of 0.832 to forecast user repeat purchases, aiding growth team in devising targeted strategies for diverse user segments.
• Conducted extensive analysis on user behavior patterns, providing valuable insights to stakeholders that guided product development and marketing strategies.

• Collaborated with engineering team to design and build data warehouse using dimensional modeling, enabling more efficient data analysis.
• Provided comprehensive data support to other business units, enabling data-driven decision making and ensuring the quality and timeliness of data requests.