Weishan He

TECHNICAL SKILLS

  • Computer Languages: Python (PyTorch, Pandas, Scikit-learn, Seaborn, etc.), SQL, R, Shell Script
  • Tools: Tableau, Looker, Git, Poetry, Docker, Google Cloud Platform, AWS, Hadoop/PySpark, FastAPI
  • Skills: Causal Inference, Machine Learning, Deep Learning, Data ETL, Data Visualization

PROFESSIONAL EXPERIENCE

Data Scientist
Andela @ USA – Aug. 2022 to Apr. 2023

  • Spearheaded experimentation, utilizing Frequentist and Bayesian approaches to design and analyze impactful A/B testing, achieving a 30% increase in the sign-up rate
  • Pioneered a recommendation engine using tree-based machine learning models and NLP to automate 30% of hiring events, reducing time-to-hire by 20%
  • Engineered data pipeline using Python and SQL to query, validate, convert, and calculate features in batch, reducing preprocessing time by 40%
  • Revamped training pipeline for diverse models, feature selection, calibration, and continuous updates, cutting training time by 50%
  • Leveraged Poetry and Git to establish and maintain mono-repo with self-developed packages, mitigating code duplication by 40% across multiple projects
  • Implemented a Docker container, API, and Git Tag to seamlessly deliver the model to the engineering team
  • Created Looker dashboards to monitor key metrics of recommendation engine, demonstrating parity with human recruiters in converting talent profile views to scheduling interview

Data Analyst (Practicum)
UC Davis Health Pharmacy @ USA – Aug. 2021 to Jun. 2022

  • Developed Tableau dashboards for pharmacists to optimize inventory management, resulting in $50,000 quarterly cost savings and 10% reduction in excess inventory

Senior Business Analyst
Mininglamp Technology Co., Ltd @ China – Aug. 2020 to Jan. 2021

  • Conducted sentiment and topic analysis on unstructured social media data, boosting sentiment score by 10% and convincing clients to extend the purchase of social media analysis

Quantitative Research Executive
Ipsos (China) Consulting Co., Ltd @ China – Jan. 2018 to Sep. 2019

  • Collaborated with the manager to lead cross-functional team of six, completing 16 marketing research projects and generating 20% annual team revenue
  • Analyzed online shopping market research data in Excel, identifying five high-potential growth scenarios for a projected 15% revenue increase
  • Mastered the firm’s market segmentation model and enhanced the Usage and Attitude study pitch book, winning a $80,000 bid

EDUCATION

Master of Science, Business Analytics
University of California, Davis @ USA – 2021 to 2022
Highlighted Coursework: Machine Learning, Time Series Analysis, Optimization, Big Data, Cloud Computing

Bachelor of Economics, International Economics and Trade
Shangdong University @ China – 2014 to 2018
Highlighted Coursework: Calculus, Linear Algebra, Statistics, Econometrics, Intermediate Macro&Microeconomics


DATA SCIENCE PROJECT

  • Stock Prediction with LSTM: built a LSTM model to predict stock price using PyTorch
  • Hotel Booking Database: Use Selenium and BeautifulSoup to scrap hotel information from booking.com and store data in JSON file, laying the foundation for modeling
  • Customer Churn Prediction & CLV: leveraged diff-in-diff to measure the short-term effect of a new feature, and used logistic regression to predict churn and calculate CLV to estimate the long-term effect
  • More Projects