Artificial Intelligence in Supply Chain Management: Investigation of Transfer Learning to Improve Demand Forecasting of Intermittent Time Series with Deep Learning

Abstract

Demand forecasting intermittent time series is a challenging business problem. Companies have difficulties in forecasting this particular form of demand pattern. On the one hand, it is characterized by many non-demand periods and therefore classical statistical forecasting algorithms, such as ARIMA, only work to a limited extent. On the other hand, companies often cannot meet the requirements for good forecasting models, such as providing sufficient training data. The recent major advances of artificial intelligence in applications are largely based on transfer learning. In this paper, we investigate whether this method, originating from computer vision, can improve the forecasting quality of intermittent demand time series using deep learning models. Our empirical results show that, in total, transfer learning can reduce the mean square error by 65 percent. We also show that especially short (65 percent reduction) and medium long (91 percent reduction) time series benefit from this approach.

Designing a double deep reinforcement learning selection tool for resilient demand prediction

“…In the literature, so many artificial intelligence forecasting architecture exist, Navneet et al used Random Forest model for forecasting fast moving consumers goods [1]. Kfier et al used the feedforward neural networks networks to forecast walmart sales [2], Chaudhuri et al used extreme learning machines with haris hawk optimization to achieve real time forecasting models [3]. Despite the profusion of forecasting methods, no single method can consistently perform equally well or poorly across all use cases.…”