Ranking and selection with two-stage decision

Tianxiang Wang, Jie Xu, Juergen Branke, Jian-Qiang Hu, Chun-Hung Chen

Abstract: Highlights•We advance Ranking & Selection (R&S) literature with new fixed-budget algorithms for two-stage R&S problems, which as to the best of our knowledge, has not been studied before.•We developed two efficient fixed-budget simulation allocation policies for two-stage R&S problems: two-stage optimal computing budget allocation (2S-OCBA) and two-stage expected value of information (2S-EVI).•We proved the consistency of the new two-stage EVI (2S-EVI) and OCBA (2S-OCBA) algorithms.•Numerical experiment results demonstrated the computational efficiency gains with the developed new algorithms compared to using single-stage fixed-budget R&S algorithms to perform simulation budget allocation for two-stage R&S problems using both benchmark test problems and a multi-product assortment problem.•Numerical results suggest that 2S-EVI tends to perform better with smaller number of decisions at first and second stage while 2S-OCBA has better performance for larger problems.