Designing a double deep reinforcement learning selection tool for resilient demand prediction
For supply chain practitioners, it offers an automated model selection tool that adapts to dataset-specific features, but the improvement is incremental.
The paper proposes a double deep reinforcement learning agent for automatic forecasting model selection in supply chain demand prediction, achieving robust performance on grocery and snack demand datasets compared to state-of-the-art methods.
The use of artificial intelligence in supply chain forecasting has attracted many scientific studies for several decades. However, the process of selecting an appropriate forecasting solution becomes a daunting task. This complexity arises due to the distinct features inherent to each dataset. Research to tackle this issue has been performed since the eighties but recent development of demand forecasting has opened new perspectives. This research aims to enhance automatic forecasting model selection by proposing a novel architecture that acts as a double deep reinforcement learning agent, selecting automatically a forecasting model from the forecasting committee at the time of prediction. Moreover, a novel early-stopping approach based on average reward convergence has been introduced to expedite training time. To evaluate the model's performance, an empirical study was conducted utilizing grocery sales datasets and snack demands datasets. The experimental results demonstrate the robustness of the proposed approach when compared to state-of-the-art methods.