Financial Trading Model with Stock Bar Chart Image Time Series with Deep Convolutional Neural Networks

By Omer Berat Sezer, A. Ozbayoglu. 2019

59 citations recorded by the source corpus.

Even though computational intelligence techniques have been extensively utilized in financial trading systems, almost all developed models use the time series data for price prediction or identifying buy-sell points. However, in this study we decided to use 2-D stock bar chart images directly without introducing any additional time series associated with the underlying stock. We propose a novel algorithmic trading model CNN-BI (Convolutional Neural Network with Bar Images) using a 2-D Convolutional Neural Network. We generated 2-D images of sliding windows of 30-day bar charts for Dow 30 stocks and trained a deep Convolutional Neural Network (CNN) model for our algorithmic trading model. We tested our model separately between 2007-2012 and 2012-2017 for representing different market conditions. The results indicate that the model was able to outperform Buy and Hold strategy, especially in trendless or bear markets. Since this is a preliminary study and probably one of the first attempts using such an unconventional approach, there is always potential for improvement. Overall, the results are promising and the model might be integrated as part of an ensemble trading model combined with different strategies.

Subfields: Computer Vision and Pattern Recognition, Finance, Management Science and Operations Research, Time-Series & Forecasting

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Weiwei Jiang
2. M. Ugur Gudelek
3. Omer Berat Sezer
4. A. Ozbayoglu

In Finance

1. Weiwei Jiang
2. M. Ugur Gudelek
3. A. Ozbayoglu
4. Omer Berat Sezer
5. Longbing Cao

In Management Science and Operations Research

1. Weiwei Jiang
2. M. Ugur Gudelek
3. Omer Berat Sezer
4. A. Ozbayoglu
5. Longbing Cao

In Time-Series & Forecasting

1. Weiwei Jiang
2. M. Ugur Gudelek
3. Omer Berat Sezer
4. A. Ozbayoglu
5. Longbing Cao

Citations in the corpus

• Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019 (2019, methodology): “In some studies [188, 189, 193, 199, 219], innovative transformations of financial time”
• Deep Learning for Financial Applications : A Survey (2020, methodology): “[62] directly used bar chart images as inputs to CNN and predicted if the image class was Buy, Hold or Sell, hence a corresponding Algo-trading model was developed.”
• Applications of deep learning in stock market prediction: recent progress (2020, methodology): “More detailed analysis about the transactions is given in Sezer & Ozbayoglu (2018, 2019).”