Risk-based estimation of manufacturing order costs with artificial intelligence

Abstract

The following paper discusses the development of a risk-based cost estimation model for completing non-standard manufacturing orders. The model in question is a hybrid of Monte Carlo Simulation (MCS), which constitutes the main module of the applied model. Vector of order risk probability, which is the input data for the MCS module, is highly difficult to assess and is burdened to a considerable degree with subjectivity, therefore it was resolved that it should be generated with the application of artificial intelligence. Depending on the accessibility of historical data, the model incorporates fuzzy logic or artificial neural networks methods. The presented model could provide support to managers responsible for cost estimation, and moreover, after slight modification also in setting deadlines for non-standard manufacturing orders.