利用群集分析與信號雜音比分類品質屬性

Using Clustering Analysis and SN Ratio to Classify Quality Attributes: An Empirical Test

黃偉嘉(Huang, Wei Chia)

指導教授 ： 蘇朝墩 ； 陳麗妃

國立清華大學/工學院/工業工程與工程管理學系/碩士(2015年)

摘要

產品及服務的品質對顧客滿意度有直接的影響，但對於顧客及消費者而言，各項服務或產品特性所造成的感受不盡相同，因此公司企業在發展經營策略前，認知各項服務與產品特性的品質屬性(quality attribute)始終極為重要；以適當的方法判別出服務或產品特性的品質屬性不僅能夠減少企業資源的浪費、更能確保企業發展利基，甚至能夠發掘出造成差異化、吸引顧客的重要項目。在判斷產品及服務的品質屬性的方法中，Kano模式普遍受到大家的歡迎，且已被廣泛的應用在各種領域及產業上，但如何能夠快速且有效的應用Kano模式找出正確的品質屬性也引發廣泛的討論。

本研究應用資料挖礦(data mining)中的群集分析之概念並結合信號雜音比發展出一套簡單快速且具相當可靠度、用於判別Kano模式中的品質屬性的方法。利用群集分析中相似度的概念配合適當的門檻劃分做出分群，接著計算信號雜音比判斷，進一步做出確切的分類；利用本研究所建構之方法於實際案例做驗證，並比較其他針對Kano模式的品質屬性分類方法，結果顯示本研究所建構之方法可靠度優於其他方法。

關鍵字

服務品質 ； 顧客滿意度 ； Kano模式 ； 群集分析 ； 信號雜音比

並列摘要

Service and product quality have the most significant and direct impact on customer satisfaction. However, customers have different impressions on various service or product quality attributes. Therefore, it is essential for enterprises to fully understand the quality attributes of their service or products. This study implemented Kano’s model to evaluate the quality attributes. The concept of Kano’s two-dimensional model evaluates quality attributes with the asymmetric and nonlinear relationship. In addition, classifying quality attributes in the Kano model with typical satisfaction data is another issue that people keen to know. The main objective of this study is to identify the quality attributes in the Kano model with the relationship between the attribute performance and customer satisfaction.
This study applied the clustering analysis and signal-to-noise ratio to determine the quality attribute of service or product characteristics in the Kano model. First, the related data were collected and the similarities of attributes were calculated. Second, the thresholds to group the attributes were defined. Finally, the signal-to-noise ratio of each attribute was computed and the quality attributes were identified. The proposed approach was validated using data collected from a food and beverage industry, showing that the proposed approach performs better than the regression methods and the other methods.

並列關鍵字

customer satisfaction ； Kano model ； clustering analysis ； quality attribute

參考文獻

Finch, H. (2005). “Comparison of distance measures in cluster analysis with dichotomous data.” Journal of Data Science, 3, 85–100

Albayraka, T., Caber, M., (2013). “Penalty–Reward-Contrast Analysis: a review of its application in customer satisfaction research.” Total Quality Management, 24(11), 1288–1300

Brant, R.D. (1987). “How service marketers can identify value-enhancing service element.” Journal of Services Marketing, 2 (3), 35–41

Chen, L. F. (2012). “A novel approach to regression analysis for the classification of quality attributes in the Kano’s model: an empirical test in the food and beverage industry.” Omega-International Journal of Management Science, 40(5), 651–659

Chen, L. F. (2014). “A novel framework for customer-driven service strategies: a case study of a restaurant chain.” Tourism Management, 41, 119–128