Skip to main content
SpringerLink
Log in

A Novel Financial Forecasting Approach Using Deep Learning Framework

  • Published:
Computational Economics Aims and scope Submit manuscript

Abstract

Moving averages, which are calculated with statistical approaches, are obtained from the price, but a horizontal market has noise problems and a trending market has lag problems. Since there is an inverse correlation between noise and delay, it is not possible to completely eliminate it with statistical approaches. In the light of the literature, it is common to obtain the classification accuracy or price estimation using regression in studies on financial forecasting. However, a high classification accuracy or a low predicted error cannot guarantee that the portfolio will win. For this reason, a Backtest process that shows the portfolio gain is also needed. This study focused on obtaining moving averages with a deep learning model instead of using statistical approaches. Better results were obtained when the moving averages were obtained with the proposed approach and the statistical approaches used the Backtest for the same periods. Experimental studies have shown that the PF is improved by an average of 9% and the trend forecast accuracy level reaches 82%.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Abbreviations

AMA:

Adaptive Moving Average

ANN:

Artificial Neural Network

ARIMA:

Autoregressive Integrated Moving Average

ARMA:

Autoregressive Moving Average

CNN:

Convolutional Neural Network

CR:

Calmar Ratio

DL:

Deep Learning

DL-MA:

Deep Learning Based Moving Average

DT:

Decision Tree

EMA:

Exponential Moving Average

GAN:

Generative Adversarial Network

GARCH:

Generalized AutoRegressive Conditional Heteroskedasticity

LSTM:

Long Short-Term Memory

MACD:

Moving Average Convergence Divergence

MAE:

Mean Absolute Error

MAPE:

Mean Absolute Percentage Error

MaxDD:

Maximum Drawdown

ML:

Machine Learning

Moving Average:

Machine Learning

PF:

Profit Factor

RF:

Random Forest

RMSE:

Root Mean Square Error

RNN:

Reccurrent Neural Network

RSI:

Relative Strength Index

SMA:

Simple Moving Average

SR:

Sharpe Ratio

WMA:

Weighted Moving Average

XGBoost:

Extreme Gradient Boosting

References

  • Amman, H. M., Tesfatsion, L., Kendrick, D. A., Rust, J., Judd, K. L., Schmedders, K., & LeBaron, B. D. (1996). Handbook of computational economics: Agent-based computational economics (Vol. 2). Amsterdam: Elsevier.

    Google Scholar 

  • Asokan, M. (2022). A study of forecasts in financial time series using machine learning methods.

  • Bao, W., et al. (2017). A deep learning framework for financial time series using stacked autoencoders and long-short term memory. PLoS ONE, 12(7), e0180944.

    Article  Google Scholar 

  • Berat Sezer, O., & Murat Ozbayoglu, A. (2019). Financial trading model with stock bar chart image time series with deep convolutional neural networks. arXiv e-prints, arXiv-1903.

  • Blümke, O. (2022). A structural hidden Markov model for forecasting scenario probabilities for portfolio loan loss provisions. Knowledge-Based Systems, 249, 108934.

    Article  Google Scholar 

  • Chen, C., et al. (2020). Financial quantitative investment using convolutional neural network and deep learning technology. Neurocomputing, 390, 384–390.

    Article  Google Scholar 

  • Dai, H., et al. (2022). Pm2.5 volatility prediction by xgboost-mlp based on garch models. Journal of Cleaner Production, 356, 131898.

    Article  Google Scholar 

  • Ding, F., et al. (2022). Interpretable cognitive learning with spatial attention for high-volatility time series prediction. Applied Soft Computing, 117, 108447.

    Article  Google Scholar 

  • Feuerriegel, S., & Gordon, J. (2018). Long-term stock index forecasting based on text mining of regulatory disclosures. Decision Support Systems, 112, 88–97.

    Article  Google Scholar 

  • Gao, R., et al. (2022). Forecasting the overnight return direction of stock market index combining global market indices: A multiple-branch deep learning approach. Expert Systems with Applications, 194, 116506.

    Article  Google Scholar 

  • Hansun, S., et al. (2021). Predicting lq45 financial sector indices using rnnlstm. Journal of Big Data, 8(1), 1–13.

    Article  Google Scholar 

  • Herzen, J., Lässig, F., et al. (2022). Darts: User-friendly modern machine learning for time series. Journal of Machine Learning Research, 23(124), 1–6.

    Google Scholar 

  • Hull, I. (2021). Machine learning for economics and finance in tensorflow 2. Berkeley, CA: Apress.

    Book  Google Scholar 

  • Kumar, R., et al. (2022). Multi-step time series analysis and forecasting strategy using arima and evolutionary algorithms. International Journal of Information Technology, 14(1), 359–373.

    Article  Google Scholar 

  • Lee, M.-C., Chang, J.-W., Yeh, S.-C., Chia, T.-L., Liao, J.-S., & Chen, X.-M. (2022). Applying attention-based bilstm and technical indicators in the design and performance analysis of stock trading strategies. Neural Computing and Applications, 34(16), 13267–13279.

    Article  Google Scholar 

  • Li, Q., et al. (2017). Web media and stock markets: A survey and future directions from a big data perspective. IEEE Transactions on Knowledge and Data Engineering, 30(2), 381–399.

    Article  Google Scholar 

  • Mehtab, S., & Sen, J. (2022). Analysis and forecasting of financial time series using cnn and lstm-based deep learning models. In Advances in distributed computing and machine learning (pp. 405–423). Springer.

  • Nazário, R. T. F., et al. (2017). A literature review of technical analysis on stock markets. The Quarterly Review of Economics and Finance, 66, 115–126.

    Article  Google Scholar 

  • Ozbayoglu, A. M., et al. (2020). Deep learning for financial applications: A survey. Applied Soft Computing, 93, 106384.

    Article  Google Scholar 

  • Santos, D. G., et al. (2022). Forecasting risk measures using intraday and overnight information. The North American Journal of Economics and Finance, 60, 101669.

    Article  Google Scholar 

  • Santur, Y. (2022). Candlestick chart based trading system using ensemble learning for financial assets. Sigma Journal of Engineering and Natural Sciences, 40(2), 370–379.

    Google Scholar 

  • Sezer, O. B., & Ozbayoglu, A. M. (2018). Algorithmic financial trading with deep convolutional neural networks: Time series to image conversion approach. Applied Soft Computing, 70, 525–538.

    Article  Google Scholar 

  • Shen, G., et al. (2021). Robust nonparametric regression with deep neural networks. arXiv preprint arXiv:2107.10343 .

  • Sherstinsky, A. (2020). Fundamentals of recurrent neural network (rnn) and long short-term memory (lstm) network. Physica D: Nonlinear Phenomena, 404, 132306.

    Article  Google Scholar 

  • Sohangir, S., et al. (2018). Big data: Deep learning for financial sentiment analysis. Journal of Big Data, 5(1), 1–25.

    Article  Google Scholar 

  • Spelta, A., et al. (2022). Chaos based portfolio selection: A nonlinear dynamics approach. Expert Systems with Applications, 188, 116055.

    Article  Google Scholar 

  • Swathi, T., et al. (2022). An optimal deep learning-based lstm for stock price prediction using twitter sentiment analysis. Applied Intelligence, 52, 1–14.

    Article  Google Scholar 

  • Tivnan, B. F., et al. (2020). Fragmentation and inefficiencies in us equity markets: Evidence from the dow 30. PLoS ONE, 15(1), e0226968.

    Article  Google Scholar 

  • Xing, F. Z., et al. (2018). Natural language based financial forecasting: A survey. Artificial Intelligence Review, 50(1), 49–73.

    Article  Google Scholar 

  • Yurttas Gunes, A., et al. (2020). Fibonacci graphs. Symmetry, 12(9), 1383.

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the TUBITAK (The Scientific and Technological Research Council of Turkey) under Grant No.: 121E733.

Funding

The authors declare that no funds, grants, or other support were received during the preparation of this manuscript.

Author information

Authors and Affiliations

  1. Firat Üniversitesi: Firat Universitesi, Elazig, Turkey

    Yunus Santur

Authors
  1. Yunus Santur
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yunus Santur.

Ethics declarations

Conflict of interest

The authors have no conficts of interest to declare that are relevant to the content of this article.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Santur, Y. A Novel Financial Forecasting Approach Using Deep Learning Framework. Comput Econ 62, 1341–1392 (2023). https://doi.org/10.1007/s10614-023-10403-5

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10614-023-10403-5

Keywords

Search

Navigation