Applications of balance optimization subset selection

Subset Selection;Netflix;Basketball;Recommendations

Dutta, Shouvik ; Jacobson ; Sheldon H.

关键词: Subset Selection;    Netflix;    Basketball;    Recommendations;   

Others  :  https://www.ideals.illinois.edu/bitstream/handle/2142/92872/DUTTA-THESIS-2016.pdf?sequence=1&isAllowed=y

美国|英语

来源: The Illinois Digital Environment for Access to Learning and Scholarship

【 摘 要 】

Balance Optimization Subset Selection (BOSS) is a framework designed to be used for causal inference on observational data. The theoretical foundation for the BOSS framework has been provided in the literature; this thesis aims to provide some examples of the practical value of BOSS by using it on two problems. The first application is using BOSS to determine a subset of users who would be suitable targets for marketing efforts, and the second application is using BOSS to identify potential first-round upsets in the NCAA basketball tournament. Finally, this thesis delves into another area of college basketball and attempts to model the process of the NCAA tournament selection committee using a decision tree.