Attribute Importance Measure Based on Back-Propagation Neural Network: An Empirical Study

Abstract

Over the years, many different importance-performance analysis (IPA) variations have emerged as it is a primary tool for analyzing customer satisfaction. One of the recent IPA variations is back-propagation neural network based importance-performance analysis (BPNN based IPA) that utilizes BPNN to measure Importance. To investigate the performance of the BPNN based IPA, the authors compared two types of BPNN models that have one and multiple output neurons referred as BPNN (regression) and BPNN (classification) respectively, with multiple linear regression (MLR). This comparison demonstrates that the BPNN (regression) does not outperform MLR in term of model accuracy and training time, yet BPNN (classification) is superior to MLR and BPNN (regression) in term of model accuracy and predictive power. This finding leads to a reconsideration of the BPNN model used in the present BPNN based IPA.

How to use importance-performance analysis (IPA)-based SWOT analysis as a new quantitative methodology for developing actual strategic plans in universities

“…When a factor has a performance ≥ the pooled mean of general performance, it will be given a positive value, in this case, the factor is a strength or an opportunity. Contrastingly, if the factor has a performance < the pooled mean of general performance, in this case, the factor is a weakness or a threat of the institution (Phadermrod, Crowder and Wills 2015).…”

“…4.). IPA-based SWOT analysis framework can be developed according to the following four steps (Phadermrod et al 2015;Nathans et al 2012):…”

“…4 Proposed framework for applying IPA-based SWOT analysis. (Phadermrod et al 2015) questionnaires are analyzed to calculate importance and performance for every single attribute of the institution's services. The procedures of this step are as follows:…”

“…Steps for conducting IPA of students' questionnaires data. (Phadermrod et al 2015) Steps for conducting IPA of students' questionnaires data are shown in Fig. 5.…”