•Feature Selection on Big Data: Helped improving one the most modern feature selection method “Model-X Knockoff filter”. Knockoffs are a powerful tool which can be used in combination with nearly any machine learning algorithm to control the false discovery rate in feature selection. I mathematically proved that the most cost efficient Knockoff filter, “second order Knockoff”, has the same power and robustness as Deep Knockoff machine. This was empirically well tested, no one could prove it. •Statistical Text Inference: I used the simple text model in Ke and Wang (2017) and design a hypothesis testing problem to test whether two documents have the same topic probability with quantified uncertainty level.

• Developed a full stack web app using AWS Amplify and reactJS, Docker, MageAI to build and deploy costom adds.• Collected +30 million social media data to increase outreach for new clientele.

Research on 4-dimensional topology. I specifically worked on slice-ribbon conjecture.