An outcome-based process optimization model using fuzzy-based association rules. Issue 6 (9th July 2018)

• Record Type: Journal Article
• Authors: Lau, Henry; Lee, C.K.M.; Nakandala, Dilupa; Shum, Paul
• Is Part Of: Industrial management & data systems. Volume 118:Issue 6(2018)
• Page Start: 1138
• Page End: 1152
• Publication Date: 2018-07-09
• Subjects: Fuzzy logic -- Data mining -- Optimization model -- Algorithms -- Association rules; Industrial management -- Periodicals; Electronic data processing -- Periodicals; Business -- Periodicals; Industrial management -- Great Britain -- Periodicals; 658.05
• DOI: 10.1108/IMDS-08-2017-0347
• Languages: English
• ISSNs: 0263-5577

Abstract

Abstract : Purpose: The purpose of this paper is to propose an outcome-based process optimization model which can be deployed in companies to enhance their business operations, strengthening their competitiveness in the current industrial environment. To validate the approach, a case example has been included to assess the practicality and validity of this approach to be applied in actual environment. Design/methodology/approach: This model embraces two approaches including: fuzzy logic for mimicking the human thinking and decision making mechanism; and data mining association rules approach for optimizing the analyzed knowledge for future decision-making as well as providing a mechanism to apply the obtained knowledge to support the improvement of different types of processes. Findings: The new methodology of the proposed algorithm has been evaluated in a case study and the algorithm shows its potential to determine the primary factors that have a great effect upon the final result of the entire operation comprising a number of processes. In this case example, relevant process parameters have been identified as the important factors causing significant impact on the result of final outcome. Research limitations/implications: The proposed methodology requires the dependence on human knowledge and personal experience to determine the various fuzzy regions of the processes. This can be fairly subjective and even biased. As such, it is advisable that the development of artificial intelligence techniques to support automatic machine learning to derive the fuzzy sets should be promoted to provide more reliable results. Originality/value: Recent study on the relevant topics indicates that an intelligent process optimization approach, which is able to interact seamlessly with the knowledge-based system and extract useful information for process improvement, is still seen as an area that requires more study and investigation. In this research, the process optimization system with an effective process mining algorithm embedded for supporting knowledge discovery is proposed for use to achieve better quality control.