An Advanced Stochastic Risk Assessment Approach Proposal Based on KEMIRA-M, QFD and Fine-Kinney Hybridization

Abstract

In this study, an advanced stochastic risk assessment approach based on integration of advanced version of quality function deployment (AV-QFD) and Modified Kemeny Median Indicator Rank Accordance (KEMIRA-M) is proposed. It is aimed to perform a new criterion weighting procedure based on four different distributions as uniform, symmetric triangular, left asymmetric triangular, right asymmetric triangular distributions. The AV-QFD includes correlations between criteria (top roof of QFD), risk degrees (RDs) of risk types (RTs) (customer needs part of QFD), correlations between RTs and criteria sets (CSs) (in the middle of QFD) to obtain the criteria priorities. Correlations on the top roof of QFD comprises three types: correlations between criteria in the first CS, correlations between criteria in the second CS and correlations between criteria in both CSs. Additionally, Fine-Kinney method is performed in AV-QFD to compute RDs of RTs in the customer needs part. Then for each expert, the correlation-based importance degree (CBID) of each criterion is obtained to rank criteria for each CS. MATLAB code was performed to see the effect of different trial numbers and replications on risk assessment. It was observed that although uniform distribution provides the best value, the same alternative ranking was obtained for all distributions. In addition, right asymmetric triangular distribution converged to the best value rapidly in practice made in this study.