Forecasting Aviation Spare Parts Demand Using Croston Based Methods and Artificial Neural Networks (original) (raw)

Accurate forecasting of spare parts demand not only minimizes inventory cost it also reduces the risk of stock-out. Though we have many techniques to forecast demand, majority of them cannot be applied to spare parts demand forecasting. Spare parts demand data usually have many zeros which makes conventional forecasting methods less effective. In this study we have used latest parametric time series methods and artificial neural networks to forecast spare parts demand of an aviation company. We have shown that with careful selection of the algorithm and their parameters the artificial neural network models give accurate forecasts for spare parts demand. Applying the proposed forecasting methods in aviation maintenance and repair companies will reduce inventory cots and eliminate risks of keeping planes on the ground. JEL Classification Codes: C45, C53.