TY - GEN
T1 - Data-driven ranking and selection
T2 - 2018 Winter Simulation Conference, WSC 2018
AU - Li, Xiaocheng
AU - Zhang, Xiaowei
AU - Zheng, Zeyu
PY - 2018/12
Y1 - 2018/12
N2 - This paper considers the problem of ranking and selection with covariates and aims to identify a decision rule that stipulates the best alternative as a function of the observable covariates. We propose a general data-driven framework to accommodate (i) high-dimensional covariates and (ii) general (nonlinear) dependence between the mean performance of an alternative and the covariates. For both scenarios, we design new selection procedures and provide certain statistical guarantees, by leveraging the data-intensive environment and various statistical learning tools. The performances of our procedures are exhibited through simulation experiments.
AB - This paper considers the problem of ranking and selection with covariates and aims to identify a decision rule that stipulates the best alternative as a function of the observable covariates. We propose a general data-driven framework to accommodate (i) high-dimensional covariates and (ii) general (nonlinear) dependence between the mean performance of an alternative and the covariates. For both scenarios, we design new selection procedures and provide certain statistical guarantees, by leveraging the data-intensive environment and various statistical learning tools. The performances of our procedures are exhibited through simulation experiments.
UR - https://www.scopus.com/pages/publications/85062618048
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85062618048&origin=recordpage
U2 - 10.1109/WSC.2018.8632388
DO - 10.1109/WSC.2018.8632388
M3 - RGC 32 - Refereed conference paper (with host publication)
T3 - Proceedings - Winter Simulation Conference
SP - 1933
EP - 1944
BT - Proceedings of the 2018 Winter Simulation Conference
PB - IEEE
Y2 - 9 December 2018 through 12 December 2018
ER -