Keynote: Personalized Policies: Theory and Application
By Aida Rahmattalabi
With a world of data at our finger prints, there is a growing interest to utilize this data to train machine learning models that can automatically make predictions about future outcomes. These predictions are used by policymakers to solve various problems across society. One of the significant applications of machine learning concerns the problem of learning treatment assignment policies that assign the optimal treatment to individuals depending on their observable characteristics. In her keynote, Susan Athey from Stanford University, shared recent advances in policy learning and hypothesis testing, with the use of historical data. She presented a variety of applications of her work, including applications for personalized treatment and contextual bandit experiments.