Hyperparameter Adaptive Neural Network Model for E-Commerce Sales Prediction

Abstract

Sales forecasting plays a vital role in the daily operations of e-commerce companies, impacting market assessment, operational planning, and supply chain management. As the market is constantly changing, accurately predicting sales is a critical challenge that e-commerce companies need to urgently address. However, traditional statistical forecasting methods have disadvantages such as long run times, low accuracy, weak generalization, and strong data periodicity, which lead to unnecessary losses for companies. We propose the QLBiGRU model that utilizes the reinforcement learning Q-Learning algorithm combined with BiGRU to improve forecasting accuracy. Automatic parameter optimization technology is also used to reduce training time and demand for hardware resources, thereby enabling enterprices to accurately analyze the market and make informed decisions.