# A Stock Price Prediction Approach Based on Time Series Decomposition and Multi-Scale CNN using OHLCT Images

arXiv: https://arxiv.org/abs/2410.19291 · HTML: https://mlsanity.com/paper/2410.19291/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 47 references that are in the map.
- First posted on arXiv 25 Oct 2024.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting](https://mlsanity.com/paper/2405.14616/) (2024)
- [Stock Price Prediction Using Convolutional Neural Networks on a Multivariate Timeseries](https://mlsanity.com/paper/2001.09769/) (2020)
- [Using Deep Learning Neural Networks and Candlestick Chart Representation to Predict Stock Market](https://mlsanity.com/paper/1903.12258/) (2019)
- [U-CNNpred: A Universal CNN-based Predictor for Stock Markets](https://mlsanity.com/paper/1911.12540/) (2019)
- [Stock Prices Prediction using Deep Learning Models](https://mlsanity.com/paper/1909.12227/) (2019)
- [Trader-Company Method: A Metaheuristic for Interpretable Stock Price Prediction](https://mlsanity.com/paper/2012.10215/) (2020)
- [Predicting Stock Market Time-Series Data using CNN-LSTM Neural Network Model](https://mlsanity.com/paper/2305.14378/) (2023)

## Built on by (most cited first, 2 of 2)

- [How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook](https://mlsanity.com/paper/2503.11835/) (2025)
- [From Local Patterns to Global Understanding: Cross-Stock Trend Integration for Enhanced Predictive Modeling](https://mlsanity.com/paper/2505.16573/) (2025)

## Abstract (arXiv)

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%.