A conceptual fuzzy-genetic algorithm framework for assessing the potential risks in supply chain management

For improving the use of logistics strategies to lower potential risks that could be generated in a supply chain, this article proposes using a fuzzy-Genetic Algorithm (GA) intelligent framework embedded with performance measurement. A fuzzy-GA approach has been developed to include fuzzy rule sets with the associated membership functions in one chromosome. This approach is composed of two phases: knowledge representation and knowledge assimilation. The related knowledge suggesting the rules of risk assessment is encoded as a compound string with fuzzy sets and their associated membership functions. The initial knowledge-based population is composed of the historical data based on performance measures, followed by knowledge assimilation in next step. GA is then employed to produce an optimal, or nearly optimal, fuzzy rule set with the corresponding membership functions for risk measures, both from the customer side and corporate side. The originality of this research is that the proposed system is equipped with the ability to assess the risk level caused by discrepancy apart from the different supply chain parties, thereby enabling the identification of the best set of decision variables.