Pendekatan Data Driven untuk Stokastik Data Envelopment Analysis (SDEA)

Abstract

This study proposed a decision-making method with a data-driven approach and robust optimization for determining performance efficiency for stochastic data envelopment analysis (SDEA) problems. Numerous situations are closely related to data uncertainty inherent in large-scale data with multi-input and multi-output. The efficiency evaluation process often involves a stochastic approach because of the uncertainty. In addition, the solution approached in the stochastic problem is still in an opportunity distribution, so a robust solution is needed to solve it. The proposed method is processed by expanding the SDEA formulation, which has a risk value and aspiration level, with a robust optimization formulation called robust stochastic data envelopment analysis (RSDEA). In testing the effectiveness of the proposed method, this study implemented a case for evaluating a university's performance and obtained a performance efficiency value of 0.89. In this proposed method, solutions can still be used to solve performance efficiency problems with large-scale multi-inputs and large-scale outputs in an uncertain environment using an efficient data-driven approach..