Demand Forecasting of Short Life Span Products: Issues, Challenges, and Use of Soft Computing Techniques

Abstract

This chapter briefly reviews forecasting features of typical data mining software, and then presents the salient features of SIMForecaster, a forecasting system developed at the Singapore Institute of Manufacturing Technology. SIMForecaster has successfully been used for many important forecasting problems in industry. Demand forecasting of short life span products involves unique issues and challenges that cannot be fully tackled in existing software systems like SIMForecaster. To introduce these problems, we give three case studies for short life span products, and identify the issues and problems for demand forecasting of short life span products. We identify specific soft computing techniques, namely small world theory, memes theory, and neural networks with special structures, such as binary neural networks (BNNs), bidirectional segmented memory (BSM) recurrent neural networks, and longshort- term-memory (LSTM) networks for solving these problems. We suggest that, in addition to these neural network techniques, integrated demand forecasting systems for handling optimization problems involved in short life span products would also need some techniques in evolutionary computing as well as genetic algorithms.