Forecasting Service Parts Demand on Automotive Industry Using Artificial Neural Network (ANN)

Abstract

Production planning in an industry, required precise decisions to made in order to determine the exact amount of product that will be produced to fulfill the customers demand. Demand forecasting is one of the most important factor in production planning process that able to generate precise production decision. The automotive industry like car manufacturer, always need an accurate demand forecast serve the uncertain demand of their products, especially the service parts product, that in fact always has uncertainty in it’s demand and frequently causing the manufacturer company lose their profit due to the backorder and overstock occurrence. Several quantitative forecasting method is used to overcome this problem, one of them is devoted for fluctuate or uncertain demand which is single exponential smoothing. The modification of this method generate croston’s method with better performance in forecasting intermittent demand. There is also artificial neural network, a machine learning computation method that could work similarly like human brain that also can forecast a non-linear data. This research is aim to compare the performance of the three forecasting method on an object with fluctuate demand. The data was gained from the demand of seven car’s service parts in an automobile manufacturer and processed using the three methods to produce forecasting with the most accurate result. The result of the calculation in this research shows that forecasting with artificial neural networks produce the most accurate forecast for the car’s service parts demand, outperform the other two methods.