A fuzzy expert system design for forecasting return quantity in reverse logistics network. Issue 3 (2014)

• Record Type: Journal Article
• Other Names: Special Editor.
• Is Part Of: Journal of enterprise information management. Volume 27:Issue 3(2014)
• Page Start: 316
• Page End: 328
• Publication Date: 2014
• Subjects: Reverse logistics -- Dimension redundancy -- Fuzzy expert systems -- Product return forecasting; Management information systems -- Periodicals; Business logistics -- Periodicals; Business -- Data processing -- Periodicals; Management -- Data processing -- Periodicals; 658.05
• DOI: 10.1108/JEIM-12-2013-0089
• Languages: English
• ISSNs: 1741-0398

Abstract

Abstract : Purpose – The purpose of this study is to develop a fuzzy expert system to design robust forecast of return quantity in order to handle uncertainties from the return process in reverse logistic network.Design/methodology/approach – The most important factors which have impact on return of products are defined. Then the factors which have collinearity with others are eliminated by using dimension redundancy analysis. By training data of selected factors with fuzzy expert system, the return amounts of alternative cities are forecasted.Findings – The performance metrics of the proposed model are found as satisfactory. That means the result of this study indicates that fuzzy expert systems can be used as a supportive tool for forecasting return quantity of alternative areas.Research limitations/implications – In the future, the proposed model can be used for forecasting other uncertain parameters such as return quality and return time. Other fuzzy systems such as type‐2 fuzzy sets can be used, or other expert systems such as artificial neural networks can be integrated into fuzzy systems.Practical implications – An application at an e‐recycling facility is conducted for clarifying how the method is used in a real decision process.Originality/value – It is the first study which aims to model an alternative forecasting by utilizing fuzzy expert system. Furthermore, a comprehensive factor list which includes predictors of the system is defined. Then, a dimension redundancy analysis is developed to reveal factors having significant impact on the return process and eliminate the rest.