Artificial intelligence methods in spare parts demand forecasting

The paper discusses the problem of forecasting lumpy demand which is typical for spare parts. Several prediction methods are presented in the article – traditional techniques based on time series and advanced methods that use Artificial Intelligence tools. The research conducted in the paper focuses on comparison of eight forecasting methods, including classical, hybrid and based on artificial neural networks. The aim of the paper is to assess the efficiency of lumpy demand forecasting methods that apply AI tools. The assessment is conducted by a comparison with traditional methods and it is based on Root Mean Square Errors (RMSE) and relative forecast errors (ex post) values. The article presents also a new approach to the lumpy demand forecasting issue – a method which combines regression modelling, information criteria and artificial neural networks.