用多尺度卷积+时序分解预测A股股价，5日预测准确率达63.37%。
A Stock Price Prediction Approach Based on Time Series Decomposition and Multi-Scale CNN using OHLCT Images
- 将价格序列转为OHLCT图像，结合多尺度卷积提取特征
- 在4454只A股上实现61.15%正向预测率和165.09%总收益
- 适合关注量化选股与视觉化金融建模的研究者
近年来，深度学习在股票预测中成为重要方向。基于图像的方法通过捕捉复杂视觉模式与空间相关性，在可解释性方面优于时序模型。然而，图像方法更易过拟合，影响预测鲁棒性。为此，本文提出一种新方法——基于序列的多尺度融合回归卷积神经网络（SMSFR-CNN），用于预测中国A股市场股价走势。通过利用卷积神经网络学习序列特征，并与图像特征融合，提升A股市场趋势预测精度。该方法缩小了图像特征搜索空间，稳定并加速了训练过程。在4,454只A股股票上的大量对比实验表明，模型对未来5天的预测达到61.15%的正向预测值和63.37%的负向预测值，总收益率达165.09%。
原文摘要 · Abstract (English)
Recently, deep learning in stock prediction has become an important branch. Image-based methods show potential by capturing complex visual patterns and spatial correlations, offering advantages in interpretability over time series models. However, image-based approaches are more prone to overfitting, hindering robust predictive performance. To improve accuracy, this paper proposes a novel method, named Sequence-based Multi-scale 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 model achieves a 61.15% positive predictive value and a 63.37% negative predictive value for the next 5 days, resulting in a total profit of 165.09%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。