Empirical decision analytics approach of advanced granularity-based models for identifying performance measures of ERPS application

Abstract

There are four motivations in this study. First, recent machine learning techniques, such as decision trees, multi-layer perceptron, and Bayesian methods, for empirical decision analytics approach are spanning a wide research interest to understand and solve a real-world complex problem and thus attract significant concerns for identifying performance measures of extensive application domains. Second, integrated circuit design (IC) industry in Taiwan plays a prominent bellwether in triggering world’s economic markets, particularly for Taiwan Semiconductor Manufacturing Company. Third, enterprise resource planning system (ERPS) has been one of the most popular tools in total solution management across industries, and its relevant decision rules attract current trends in using an advanced soft computing approach. Lastly, with limited literature reviews, there is scarce investigation on picking right ERPS with effective decision rule-based knowledge for the IC design industry from application perspectives, and this research is first to bridge such a study gap for technical and managerial applications. Thus, this research synthesizes and proposes an advanced hybrid procedure to organize multi-expert granularity-based models with comprehensible decision rule-based wisdom to experience the ERPS selection and identify its determinants. The study finding implies that the determinants are varied from the class types and benefit interested parties useful references to facilitate positive migration of inter-industry. This research significantly contributes clear motivation and originality with good application values for an advanced hybrid analysis.