Optimizing of Universal DEA Model with Multi-Level Integration under Neutrosophic Environment

This research introduces a comprehensive Universal Data Envelopment Analysis (DEA) model to handle real-world problems fraught with uncertainty of every operational facet. Apart from all this, this framework has a feature of embracing many level variations: deterministic, stochastic, fuzzy, and neutrosophic, in both input and output variables, unlike the traditional DEA models, which are limited to deterministic. Besides accommodating different orientation types detected in models such as inputoriented and output-oriented, it also incorporates variable and constant return types of scale. The main objective of this study is to develop a flexible DEA model that can measure and rank, under uncertain conditions, the performance efficiency of organizations having comparable input-output structures. The proposed model seeks to identify inefficient organizations so as to improve specifically on those areas to have a much better outcome in overall efficiency. This provides decision-makers with very strong and versatile options for efficient measures, even in the context of heterogeneous and imprecise data. The paradigm for this study lies in bringing together several ways of handling uncertainty under one umbrella. This study is much better than the conventional DEA models. Possible restrictions, however, on applicability in very large data sets and computation time complexities would need further probing.