Yuchen Wang

Facebook Research, Menlo Park, CA (2019)

Using machine learning algorithm to decide personalize reserve price for second price auction in advertisement. Find potential opportunity to improve the total revenue.

Find advertisement market abstractions for simulation by matrix completion and clustering method. Can be used to predict the result of Budget A/B Test. Plan to write a paper about this.

MIT Operations Research Center, Cambridge, MA (2015-now)

Advisor: Prof. Dimitris Bertsimas

Developing interpretable machine learning algorithm using optimizations, mainly on optimal decision trees and optimal clustering method. Working on applications in transplantation and pediatrics.
Massachusetts Institute of Technology, Cambridge, MA (2015)

Advisor: Prof. Hui Chen

We worked on the option pricing of China’s stock European options using binomial price tree which helped to model T+1 mechanism and no-short selling policy.

Massachusetts Institute of Technology, Cambridge, MA (2018)

Teaching Assistant for 15.089 Machine Learning Under a Modern Optimization Lens

Conducted weekly recitations about machine learning and optimization for 60 students, created and graded six problem sets and midterms. Graded final project.
Massachusetts Institute of Technology, Cambridge, MA (2017)

Teaching Assistant for 15.089: The Analytics Capstone

Mentored four Masters of Business Analytics from Sloan School of Business to do projects with McKinsey & Company. The topics are about the spatiotemporal analysis of industrial agglomeration and extract named topics from unlabeled text.

"Development and validation of an Optimized Prediction of Mortality (OPOM) for candidates awaiting liver transplantation" with D. Bertsimas, J. Kung, N. Trichakis, R. Hirose, P. Vagefi, 2018, American Journal of Transplantation.
"Comparison of Machine Learning Optimal Classification Trees With the Pediatric Emergency Care Applied Research Network Head Trauma Decision Rules." with D. Bertsimas, J. Dunn, S.Dale, T. Trikalinos, 2019, JAMA Pediatrics.
"Visualizing tradeoffs in liver transplantation: the benefits of a continuous distribution model and its implications for national policy development" with D. Bertsimas, T. Papalexopoulos, N. Trichakis and P. Vagefi, accepted by Transplanation.

"Optimal Nonlinear Trees for Predictions" with D. Bertsimas and J. Dunn, submitted.
"Optimal Predictive Clustering" with D.Bertsimas and M.Sobiesk, working paper.

Education.