Yiming(Larry) Tan Email & Phone Number

Shanghai, China

Princeton, New Jersey, United States

- Developed automated AI products utilizing Django and ML&DL framework(TensorFlow, Pytorch, sklearn, OpenCV).- Improved image text detection pipeline to support multiple use cases including desensitilization and OCR on various documents.- Built web-based image classification model training pipeline for insurance documents.- Used Tesseract OCR，OpenCV and template-based approach to complete information extraction from blood test report.- Responsible for resource and efficiency management in AI products (GPU allocation, memory management, parallelism, etc.)

Greater New York City Area

Columbus, Ohio Area

- Built up predictive models for glaucoma and Alzheimer with medical and genetics data from UKBiobank (1GB~1TB) on a Linux super computer server with Python ,R and Shell scripts- Extracted features from genetic data by calculating PRS using LDpred model to reduce extremely large dimensions- Applied machine learning models (XGBoost, Logistic Regression, Gaussian Naïve Bayesian and Neural Network) for prediction, and used CV and Bayesian Optimization for tuning hyperparameters

Greater New York City Area

- Prepare, complete and showcase various data science projects and topics including Tweets Explorations via API & Topic Modelling, Comparisons between ML Prediction Models in Educational Background, Unsupervised Learning (Clustering & Dimension Reduction) in Image Analysis, Study on Interpretability of ML & Black Box Models- Design and deliver data-focused lectures with hands-on practice in R and Python for community development

Shanghai, China

Utilized Excel (functions and VBA) and R to analyze, visualize and model complex data and complete monthly reportsMaking sales performance analysis, predictions and target setting on internal and external data to support sales force efficiency improvement initiatives

Shanghai City, China

Developing data cleansing programs with Excel and VBA to deal with missing data.Monitoring the development of Small & Medium-sized Enterprises in Shanghai.

Shanghai City, China

-Applied knowledge in computer network, algorithm analysis, and relational databases to design the database management system for network switches

Master'S Degree, Statistics, 4.08

Courses: Probability and Inference, Linear Regression, Statistical Computing, Algorithm in Data Science, Statistical Machine Learning.

Bachelor'S Degree, Statistics, 3.68(Major)

Courses: Mathematical Analysis, Advanced Algebra, Probability and Inference, Statistical Learning, Time Series, Multivariate Statistics.