Improved methodology in risk analysis with stochastic simulation for termination of Indonesia's fuel subsidy

Background and Objective: The Indonesian fuel oil supply chain system is a complex system influenced by probabilities and uncertainties. This study intends to solve issues in Supply Chain Risk Management (SCRM) in a complex Indonesian fuel system through investigating variables in multivariate data and risk management framework, as well as to develop new market structure potential. Materials and Methods: The study offers a stochastic optimisation simulation based on Monte Carlo sampling and a risk-based compliance audit on the existing system of Supply Chain Risk Management (SCRM) using a state-of-the-art FIRST (Fairness, Independent, Reliable, Sustainable, Transparent) likelihood factor. This is combined with sensitivity analysis, where risk measures are determined pursuant to non-metric data as indicator variables of consequences factors using focus group discussion mechanism multivariate data analysis. Results: The result of this research showed that Monte Carlo simulation-based methods for stochastic optimisation of risk measures, supported by FIRST new variables as likelihood factor, can produce a level of priority that represents new integrated risk mitigation solution. It allows integrated and measured investigation and problem solving of complex system, such as security of a subsidised fuel supply in Indonesia and identification of other potential risks in supply chain risk management for market structure development. Conclusion: This study provides a theoretical and practical contribution to the use of Monte Carlo sampling in simulation optimisation of risk measures by formulating new likelihood factors. Subsequently, risk analysis can be performed because of repeated simulated correlation in optimisation (cross-entropy), which is useful for researchers as well as practitioner.