Experience

National Center for Supercomputing Applications

• United States
• Research Services
• 100 - 200 Employee

• Intern

  • Jun 2020 - Present

  1. Participated in the CDC 2020 WNV Forecast Competition. We included history records, weather, economics and other features in the model and conducted significant analysis to them. Given the data sparsity, we applied zero-inflated model + random forest in Python to predict the case numbers and gained 90% accuracy on our testing set. 2. Participating in building bioinformatics pipelines on Google Cloud. Being responsible for the optimization and containerization, as well as testing of the pipeline. This pipeline will be applied in real cancer genomics analysis.



Insigma Enpu Software Limited

• Data Scientist Intern

  • Oct 2018 - Jan 2019

  1. Performed data preprocessing on Hangzhou laboring datasets containing 800,000+ records and 300+ columns, which is then applied to predicting companies’ risk of illegal labor behaviors.2. Drafted reports about the project progress and algorithms used, which were adopted as the main report delivered to clients. 1. Performed data preprocessing on Hangzhou laboring datasets containing 800,000+ records and 300+ columns, which is then applied to predicting companies’ risk of illegal labor behaviors.2. Drafted reports about the project progress and algorithms used, which were adopted as the main report delivered to clients.