Paper ID: 2410.19291
A Stock Price Prediction Approach Based on Time Series Decomposition and Multi-Scale CNN using OHLCT Images
Zhiyuan Pei, Jianqi Yan, Jin Yan, Bailing Yang, Ziyuan Li, Lin Zhang, Xin Liu, Yang Zhang
Stock price fluctuations are influenced by a variety of factors, including macroeconomic conditions, government policies, and market sentiment, which together make price movements complex and difficult to predict. Despite many studies aimed at enhancing stock price prediction models, challenges such as data noise, model overfitting, and lack of interpretability are still encountered. To address these issues and improve prediction accuracy, this paper proposes a novel method, named Sequence-based Multiscale Fusion Regression Convolutional Neural Network (SMSFR-CNN), for predicting stock price movements in the China A-share market. By utilizing CNN to learn sequential features and combining them with image features, we improve the accuracy of stock trend prediction on the A-share market stock dataset. This approach reduces the search space for image features, stabilizes, and accelerates the training process. Extensive comparative experiments on 4,454 A-share stocks show that the proposed model achieves 61.15% for positive predictive value and 63.37% for negative predictive value of the stock price trend over the next 5 days, resulting in a total profit of 165.09%.
Submitted: Oct 25, 2024