An Online Retail Prediction Model Based on AGA-LSTM Neural Network

With the development of e-commerce, the scale of online retail is becoming larger and larger. The prediction of sales volume is facing the challenges of various categories and changeable customer demands. Based on this, this paper proposes an online retail prediction model based on AGA-LSTM neural network. In the process of building LSTM neural network, the adaptive genetic algorithm (AGA) is used to optimize the network parameters such as time step, hidden layer number and training times to improve the prediction accuracy of the model, and it is used to forecast the types of goods and the total sales volume. The results on the Online Retail II dataset in UCI show that the prediction accuracy of AGA-LSTM model is greatly enhanced compared with the traditional LSTM model, which verifies the effectiveness of this algorithm.