Transitioned SAS Oracle based analytics system to automated analytics pipeline with Python, Pyspark for ETL, Spark-ml for Recommendation Engine and automated workflow using Airflow; reduced analysis time by 92%.

Created model based on LSTM architecture to find rare diseases in patients via EHR data utilizing Python and Pytorch, improving ROC to 0.73 from 0.61 used by previous models.

Built RESTful API in Flask to serve model and used Docker for microservices to productionize system.

Analyzing data and created Random Forest and Xgboost machine learning models for internal tool to help in predicting project's turnaround time and budget using Python and Scikit-learn.

Analyzed data with Pandas and Matplotlib to understand why human forecast did not work well and created deep learning model to predict total hours of project; models improved MSE by over 150%.