Improved Generative Adversarial Network Stock Price Prediction Method

Abstract

In response to the challenges posed by the nonlinearity, instability, and complexity of the stock market in the insurance industry, we propose an enhanced generative adversarial neural network-based stock prediction model termed CAL-WGAN-GP. The model's generator incorporates components such as the CNN-BiLSTM model and a self-attention mechanism, employed to generate precise predictions for stock closing prices. The discriminator, comprising a multi-layer convolutional neural network, is tasked with distinguishing between the stock closing prices generated by the generator and actual stock closing prices. To assess the model's generalization capability, stock data from China Ping an, China Life, XinHua Insurance, and Pacific Insurance is selected. During the dataset construction, relevant features, including technical indicators, are incorporated to facilitate the model in better learning hidden data information. Experimental results demonstrate that CAL-WGAN-GP urpasses baseline models across four evaluation metrics: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R2), achieving the highest degree of data fitting