Managing Risk and Uncertainty in Machine Replacement Decisions Using Real Options Analysis and Monte Carlo Simulation

Abstract

Abstract The present research discusses the application of risk management tools and Real Option Analysis (ROA) to assess and quantify managerial flexibility in machine replacement decisions under uncertain conditions. Different management configurations are used for the real options approach: options to execute, options to delay, and options to cancel. This reflects the uncertainty inherent to each stage of planning. Uncertainties such as future demand and life-cycle costs are implemented in the model as probability distributions. Monte Carlo simulation is employed to deal with such uncertainties and to facilitate experimental trials. The net present value is used as a decision criterion to determine the best replacement option under different replacement and real option scenarios. Herein, a case study to evaluate different replacement alternatives was conducted for the garment industry. Results of the stochastic net present value, mean-standard-deviation scatter plot, and stochastic dominance showed that the best option was to rent and then buy a new machine of reduced size but greater technological advancement. Finally, tornado diagrams and perfect control methods were used to analyze uncertain factors in order to improve the model and further minimize uncertainty effects.