Stock price forecasting based on improved time convolution network
Authors:
- 22 March 2022
- journal article
- research article
- Published by Wiley in Computational Intelligence
- Vol. 38 (4) , 1474-1491
Abstract
Stock forecasting is difficult because of its complexity and uncertainty. To better predict stock prices and then provide stockholders with reasonable suggestions, this paper proposes an improved time convolution network (TCN) model for predicting stock prices. The model used can make up for some of the shortcomings of the traditional neural network, use the trading data in the stock market, and put the preprocessed data of financial news into the model for training to improve the accuracy of prediction. Using the Shanghai Securities Exchange (SSE) 50 Index (Shanghai Securities Exchange 50 Index selects the most representative 50 stocks with large scale and good liquidity in Shanghai stock market as sample stocks) and news text crawled from financial web pages as samples, predict the direction of the SSE 50 Index's rise and fall. After using different network structure hyperparameters to adjust the model structure, the prediction effect is compared with other models, and it is found that the proposed improved TCN model can effectively improve the effect of predicting the rise and fall of the SSE 50 index, and can complete the model training and predict the stock price faster.Keywords
This publication has 9 references indexed in Scilit:
- Real-time electricity price forecasting of wind farms with deep neural network transfer learning and hybrid datasetsApplied Energy, 2021
- Probabilistic forecasting with temporal convolutional neural networkNeurocomputing, 2020
- Temporal Convolutional Networks for the Advance Prediction of ENSOScientific Reports, 2020
- Deep Learning Approach for Short-Term Stock Trends Prediction Based on Two-Stream Gated Recurrent Unit NetworkIEEE Access, 2018
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Temporal Convolutional Networks: A Unified Approach to Action Segmentation2016
- Deep Residual Learning for Image Recognition2016
- A LSTM-based method for stock returns prediction: A case study of China stock market2015
- Fully convolutional networks for semantic segmentation2015