December 22, 2024
Ahmad Ghorbanpour

Ahmad Ghorbanpour

Academic Rank: Assistant professor
Address:
Degree: Ph.D in Industrial management
Phone: 09112919807
Faculty: School of Business and Economics

Research

Title
Discriminant Analysis of the Circular Economy Performance of Manufacturing Industries Using Machine Learning Algorithms
Type Thesis
Keywords
ارزيابي افتراقي، عملكرد اقتصاد چرخشي، صنايع توليدي، يادگيري ماشين.
Researchers maryam bakhtar (Student) , Ahmad Ghorbanpour (Primary advisor) , Khodakaram Salimifard (Advisor)

Abstract

Background: In recent years, companies need a new economic model for sustainable development to defend the environmental and sustainable values of society. As an efficient tool, the circular economy can reduce environmental impacts and prevent increased costs, delays and other consequences and help organizations achieve better performance. Aim: The aim of this research is to is to evaluate the differential performance of the circular economy of manufacturing industries. Methodology: This research is applied in terms of purpose and descriptive in terms of method and nature. The statistical population of this research includes the active manufacturing industries of Bushehr province, which were selected using the Cochran sample size method. The data collection tool of this research is a researcher-made questionnaire, the validity of which was confirmed by the formal content analysis method and its reliability was confirmed by the Cronbach's alpha method. To achieve the goals, machine learning approaches have been used. Conclusions: The results showed that the manufacturing industries of the first cluster had a relatively good performance in the gas consumption feature and in other features their performance was below average. The manufacturing industries of the second cluster had a relatively good performance in the characteristics of investment in environmentally friendly technologies and equipment, employees active in the field of environment and green energy consumption. In other features, their performance is below average. The results of the diagnostic analysis showed that the provided prediction function has a very high diagnostic power for the cleaning industry.