Yuan du

About Yuan du

9+ years of experience in Prospective and Retrospective studies, Causal inference, and Predictive modeling.• Techniques: SQL, R (Tidyverse, glmnet, caret, Rmarkdown, ggplot), Python (Numpy, Pandas, Scikit-learn, Matplotlib, Pytorch, Tensorflow), Databricks, PySpark, SAS, distributed multicores computing, Github version control• Proficient in developing advanced analytics solutions based on machine learning and predictive modeling for research publications and business decisions with effective communication• Machine Learning: Penalized regression (Lasso, Ridge), Support Vector Machine, Decision Tree, Random Forest, GBM, Clustering(K-Means, GMM), Dimension Reduction (PCA, t-SNE)• Statistical Modeling: Casual inference, Generalized Liner Model (GLM), Mixed model (GLMM), Hypothesis Testing, Propensity Score Matching, Randomization, Power Analysis, Survival analysis, Meta-analysis, Bayesian methods• Deep Learning: Generative AI models, Adversarial attack and defense, Energy Based Models (EBMs), Diffusion ModelsFor more info, please visit my blog: yuan-du.com

Experience

1. Principal Data Scientist

   UnitedHealth Group

   May 2024 — Present

Education

• University of Central Florida

  Master of Science (M.S.), Statistics and Data Science

  2013 — 2015

• University of Central Florida

  Doctor of Philosophy - PhD, Big Data Analytics

  2019

• Influencer Marketing

  Bachelor of Science (B.S.), Economic Statistics

  2006 — 2010

Skills

• Statistical Modeling
• Statistical Software
• Jmp
• Chinese
• Data Analysis
• Power Analysis
• Hypothesis Testing
• R
• Python
• Outlook
• Microsoft Office
• Statistics
• Data Mining
• Research
• Sas
• Statistical Data Analysis
• Survival Analysis
• Spss
• Powerpoint