Data envelopment analysis with imprecise data: Fuzzy and interval modeling approaches

Data Envelopment Analysis with inaccurate data poses a significant challenge in data science and analytics due to the inherent uncertainties and discrepancies present in real-world data. This article investigates the performance of units evaluated with inaccurate data and presents modeling approache...

Full description

Saved in:
Bibliographic Details
Main Authors: Hassan Mishmast Nehi, Faranak Hosseinzadeh Saljooghi, Amir Rahimi, Laxmi Rathour, Lakshmi Narayan Mishra, Vishnu Narayan Mishra
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Results in Control and Optimization
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666720725000177
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Data Envelopment Analysis with inaccurate data poses a significant challenge in data science and analytics due to the inherent uncertainties and discrepancies present in real-world data. This article investigates the performance of units evaluated with inaccurate data and presents modeling approaches, including fuzzy and interval methodologies. In other words, by examining the effectiveness of units evaluated with interval data with fuzzy or interval-based bounds, novel approaches for modeling data coverage issues are introduced. Various mathematical techniques and analytical processes are utilized to solve problems and prove theorems. The primary focus is on modeling data coverage issues with fuzzy or interval bounds, which facilitates the creation of more accurate and effective representations of uncertain data. The findings of this article indicate that these modeling approaches lead to improvements in data-driven decision-making. Practical applications of these methods include information management and decision-making for DMU sets in fuzzy and interval environments, enabling analysts to make better decisions. This research contributes to advancing the field of data analytics by providing systematic methods for managing and analyzing inaccurate data, thereby enhancing the reliability and applicability of insights based on data foundations.
ISSN:2666-7207