CV

Education

• M.S. in Data Science and Machine Learning, National University of Singapore, Aug 2024 – Dec 2025
• B.S. in Statistics, East China Normal University, Sep 2020 – Jun 2024

Internships

• Nov 2024 – NOW: NUS - Data Science Teaching Assistant
  • Assisted professor in workshop, covering topics such as Airflow workflow management, deep learning with PyTorch, and business problem-solving using Retrieval-Augmented Generation (RAG) and LangChain frameworks. Documented the problems and solutions for future reference and easy access.
• Feb 2024 – Jul 2024: LVMH - Data Modeling Intern
  • Feature Engineering: Cleaned and explored large-scale user and product data using Dataphin SQL, building over 1,000 features related to users and products, enhancing the foundational quality of data analysis.
  • Model Analysis: Assisted in implementing models based on brand requirements, specifically for predicting potential customers using machine learning. Developed an XGBoost model to forecast user purchasing behavior, adjusted the model according to business needs, achieving an AUC of 0.8 and increasing purchase rate by 350%-440%.
  • Dashboard Development: Built real-time data monitoring dashboards using QuickBI, covering user purchase metrics (AUS, IPT, etc.), model performance, and data source quality, improving decision-making efficiency in business data.
• Jul 2023 – Nov 2023: Zhongyan Technology - Research Intern
  • Data Analysis: Assisted the research department in preparing reports for brand clients. Extracted core keywords from McDonald’s review data and performed. Visual analysis to interpret user satisfaction, proposing targeted marketing strategies.
  • Statistical Analysis: Conducted statistical analysis on survey data from Jiuyang across multiple regions, including \textbf{significance testing}, to provide data support for product market positioning and user profiling.
  • Tool Development: Developed a web scraping tool based on Python Selenium and Requests libraries, significantly improving data collection efficiency by 60% through the rapid extraction of massive amounts of store and review data.

Skills and Hobby

• Programming Skills: Python, SQL, R, QuickBI, SPSS, ThinkCell
• Analytical Skills: Machine Learning, Experimental Design, Casual Inference, Data Visualization, Data Crawling
• Languages: Proficient in English and Mandarin
• Hobby: Guzheng Level 10