A Data Mining Approach to the Analysis of a Catering Lean Service Project. Issue 2 (3rd April 2017)

• Record Type: Journal Article
• Authors: Pan, Wen-Tsao; Leu, Yungho; Zhu, Wenzhong; Lin, Wei-Yuan
• Is Part Of: Intelligent automation & soft computing. Volume 23:Issue 2(2017)
• Page Start: 243
• Page End: 250
• Publication Date: 2017-04-03
• Subjects: Quantile regression -- lean service -- grey relational analysis -- artificial intelligence -- neural networks; Artificial intelligence -- Periodicals; Intelligent control systems -- Periodicals; 003.5
• DOI: 10.1080/10798587.2016.1203564
• Languages: English
• ISSNs: 1079-8587

Abstract

Abstract: Applied quantile regression to explore different ways to improve the catering service so as to promote the customer's service satisfaction.A lean service project aims to reduce the cost of material, labor and time required in providing a service to a customer so as to promote the service satisfaction from the customer. This paper presents a data mining approach to analyze the effectiveness of a lean service project on a catering service provided by a university restaurant. We have designed three consecutive stages of service scenarios; each represents an improvement over its previous stage. In this study, we first applied the grey relational analysis to confirm the effectiveness of the lean service project. That is, stage two and three actually obtained higher service satisfaction from customers than their corresponding previous stages did. We have performed a quantile regression analysis to explore the effect of different factors on low and high quantiles of service satisfaction. The result of the quantile regression analysis provides different ways for the restaurant to improve its customer's service satisfaction. Finally, we have built several prediction models to forecast the service satisfaction (Poor or Good) of a service sample. The experimental result showed that among the eight prediction models, FOAGRNN is the best in terms of the sensitivity, specificity, AUC and Gini performance measures.