Research on Inventory Management and Demand Forecasting of E-commerce Platform Based on ARIMA and LSTM Models

This paper focuses on an in-depth study of inventory management issues in e-commerce platforms. Merchants need to balance between the high capital pressure caused by more inventory and the risk of out-of-stock that may be caused by less inventory. Firstly, this paper preprocesses the data of the e-commerce platform, merges the time series data, and deals with the outliers, forecasts the demand for goods through the ARIMA model, and evaluates the model effect by using the RMSE and 1-wmape indicators. Secondly, for the data of new products due to insufficient sample size, this paper used K-means clustering model for similarity classification and predicted future sales accordingly. Finally, for large-scale promotions, this paper predicts the demand under the influence of promotions through data preprocessing and LSTM model, and the 1-wmape indicator shows that the prediction effect of LSTM model is better than that of ARIMA model. The methods and conclusions of this study are of great practical significance for optimizing the inventory management of e-commerce platforms and improving supply chain efficiency.