Yi Su, a doctoral student in Statistics and Data Science, has been named one of four recipients of the 2019-2020 Bloomberg Data Science Ph.D. Fellowship.
Advised by Cornell Computing and Information Science Professor Thorsten Joachims, Su researches machine learning methods and applications, specifically counterfactual learning and its applications on online systems.
Her research project, "Off-Policy Evaluation and Learning for Interactive Systems," looks at machine learning algorithms used in search engines, recommender systems, and other user interactive systems. These algorithms are improved through a "recurrent loop" that typically involves learning from newly collected data, making improvements to the features and the model, and then testing the new system online, Su said.
“My goal is to fundamentally speed up this process through new counterfactual inference techniques that move both learning and evaluation from ‘online’ to ‘offline,” she said.
The Bloomberg Fellowship provides support to young scholars early in their careers and includes an internship this summer at the financial software company. It will prove a fantastic opportunity to work with real-world, decision-making problems, Su said.
“These challenges will bring me new perspectives and fresh ideas,” she said, “and I am excited to tackle these tough problems, which will have a real impact on Bloomberg Terminal,” the company’s software system.
“I would like to thank my advisor Thorsten Joachims, who encourages me and gives me unwavering support on this,” she said.