Integration of stochastic and robust optimization techniques into DEA model for more accurate and reliable efficiency estimation

Abstract

Efficiency assessment is vital to assessing decision-making units (DMUs) in numerous sectors. DEA is a prominent non-parametric efficiency assessment tool. Traditional DEA models assume deterministic inputs and outputs, ignoring real-world uncertainties and variability. To improve efficiency estimation, stochastic and robust optimization approaches can be integrated into DEA models. To improve efficiency estimation, we present a stochastic and robust optimization framework incorporating DEA. Probabilistic inputs and outputs allow stochastic optimization to account for uncertainty. The model can capture data variability and create stochastic DMU efficiency scores by adding probability distributions. For data uncertainties and outliers, the DEA model uses robust optimization. Robust optimization considers worst-case scenarios and minimizes extreme observations on efficiency estimation. This makes efficiency scores more resilient to data outliers and noise.  DEA models benefit from stochastic and resilient optimization. First, considering data uncertainties and fluctuations improves DMU efficiency representation. Second, eliminating outliers and extreme observations improves efficiency estimation. Third, efficiency scores help decision-makers make better, more informed choices. A case study in a specific industry shows the framework's efficacy. We compare classic and integrated stochastic-robust DEA model outcomes. The integrated model provides more accurate and dependable efficiency estimates, helping decision-makers understand DMU performance. DEA models with stochastic and resilient optimization increase efficiency estimation. By considering uncertainties and outliers, this paradigm helps decision-makers evaluate DMUs in many sectors more accurately and reliably.