Financial Forecasting using Deep Learning with an Optimized Trading Strategy

Anuar Maratkhan, Ibrakhim Ilyassov, Madiyar Aitzhanov, M. Fatih Demirci, Murat Ozbayoglu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Financial forecasting using computational intelligence nowadays remains a hot topic. Recent improvements in deep neural networks allow us to predict financial market behavior. In our work we first implement a novel approach of [1], which converts financial time-series data to 2-D images and then feeds the generated images to a convolutional neural network as an input. We then hypothesize that the performance of the model can be improved using different techniques. Specifically, in our work, we improve the computational and financial performance of the previous approach by 1) fine-tuning the neural network hyperparameters, 2) creating images with 5 channels corresponding to indicator clusters, 3) improving financial evaluation using take profit and stop loss techniques, 4) evolutionary optimized parameters for trading strategy. The results of this study show that the above-mentioned strategies improve the model considerably. We conclude with future work that can be done in order to further improve the computational and financial performance of the model.

Original languageEnglish
Title of host publication2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages838-844
Number of pages7
ISBN (Electronic)9781728121536
DOIs
Publication statusPublished - Jun 2019
Event2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Wellington, New Zealand
Duration: Jun 10 2019Jun 13 2019

Publication series

Name2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings

Conference

Conference2019 IEEE Congress on Evolutionary Computation, CEC 2019
CountryNew Zealand
CityWellington
Period6/10/196/13/19

Fingerprint

Trading Strategies
Forecasting
Neural Networks
Neural networks
Hyperparameters
Financial Data
Financial Time Series
Computational Intelligence
Financial Markets
Time Series Data
Artificial intelligence
Convert
Profit
Time series
Tuning
Profitability
Model
Predict
Evaluation
Learning

Keywords

  • convolutional neural networks
  • cuckoo search
  • deep learning
  • financial forecasting
  • time-series classification

ASJC Scopus subject areas

  • Computational Mathematics
  • Modelling and Simulation

Cite this

Maratkhan, A., Ilyassov, I., Aitzhanov, M., Demirci, M. F., & Ozbayoglu, M. (2019). Financial Forecasting using Deep Learning with an Optimized Trading Strategy. In 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings (pp. 838-844). [8789932] (2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CEC.2019.8789932

Financial Forecasting using Deep Learning with an Optimized Trading Strategy. / Maratkhan, Anuar; Ilyassov, Ibrakhim; Aitzhanov, Madiyar; Demirci, M. Fatih; Ozbayoglu, Murat.

2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 838-844 8789932 (2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Maratkhan, A, Ilyassov, I, Aitzhanov, M, Demirci, MF & Ozbayoglu, M 2019, Financial Forecasting using Deep Learning with an Optimized Trading Strategy. in 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings., 8789932, 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 838-844, 2019 IEEE Congress on Evolutionary Computation, CEC 2019, Wellington, New Zealand, 6/10/19. https://doi.org/10.1109/CEC.2019.8789932
Maratkhan A, Ilyassov I, Aitzhanov M, Demirci MF, Ozbayoglu M. Financial Forecasting using Deep Learning with an Optimized Trading Strategy. In 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 838-844. 8789932. (2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings). https://doi.org/10.1109/CEC.2019.8789932
Maratkhan, Anuar ; Ilyassov, Ibrakhim ; Aitzhanov, Madiyar ; Demirci, M. Fatih ; Ozbayoglu, Murat. / Financial Forecasting using Deep Learning with an Optimized Trading Strategy. 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 838-844 (2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings).
@inproceedings{f243a14f19f841b3b6fb50feefacc372,
title = "Financial Forecasting using Deep Learning with an Optimized Trading Strategy",
abstract = "Financial forecasting using computational intelligence nowadays remains a hot topic. Recent improvements in deep neural networks allow us to predict financial market behavior. In our work we first implement a novel approach of [1], which converts financial time-series data to 2-D images and then feeds the generated images to a convolutional neural network as an input. We then hypothesize that the performance of the model can be improved using different techniques. Specifically, in our work, we improve the computational and financial performance of the previous approach by 1) fine-tuning the neural network hyperparameters, 2) creating images with 5 channels corresponding to indicator clusters, 3) improving financial evaluation using take profit and stop loss techniques, 4) evolutionary optimized parameters for trading strategy. The results of this study show that the above-mentioned strategies improve the model considerably. We conclude with future work that can be done in order to further improve the computational and financial performance of the model.",
keywords = "convolutional neural networks, cuckoo search, deep learning, financial forecasting, time-series classification",
author = "Anuar Maratkhan and Ibrakhim Ilyassov and Madiyar Aitzhanov and Demirci, {M. Fatih} and Murat Ozbayoglu",
year = "2019",
month = "6",
doi = "10.1109/CEC.2019.8789932",
language = "English",
series = "2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "838--844",
booktitle = "2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings",
address = "United States",

}

TY - GEN

T1 - Financial Forecasting using Deep Learning with an Optimized Trading Strategy

AU - Maratkhan, Anuar

AU - Ilyassov, Ibrakhim

AU - Aitzhanov, Madiyar

AU - Demirci, M. Fatih

AU - Ozbayoglu, Murat

PY - 2019/6

Y1 - 2019/6

N2 - Financial forecasting using computational intelligence nowadays remains a hot topic. Recent improvements in deep neural networks allow us to predict financial market behavior. In our work we first implement a novel approach of [1], which converts financial time-series data to 2-D images and then feeds the generated images to a convolutional neural network as an input. We then hypothesize that the performance of the model can be improved using different techniques. Specifically, in our work, we improve the computational and financial performance of the previous approach by 1) fine-tuning the neural network hyperparameters, 2) creating images with 5 channels corresponding to indicator clusters, 3) improving financial evaluation using take profit and stop loss techniques, 4) evolutionary optimized parameters for trading strategy. The results of this study show that the above-mentioned strategies improve the model considerably. We conclude with future work that can be done in order to further improve the computational and financial performance of the model.

AB - Financial forecasting using computational intelligence nowadays remains a hot topic. Recent improvements in deep neural networks allow us to predict financial market behavior. In our work we first implement a novel approach of [1], which converts financial time-series data to 2-D images and then feeds the generated images to a convolutional neural network as an input. We then hypothesize that the performance of the model can be improved using different techniques. Specifically, in our work, we improve the computational and financial performance of the previous approach by 1) fine-tuning the neural network hyperparameters, 2) creating images with 5 channels corresponding to indicator clusters, 3) improving financial evaluation using take profit and stop loss techniques, 4) evolutionary optimized parameters for trading strategy. The results of this study show that the above-mentioned strategies improve the model considerably. We conclude with future work that can be done in order to further improve the computational and financial performance of the model.

KW - convolutional neural networks

KW - cuckoo search

KW - deep learning

KW - financial forecasting

KW - time-series classification

UR - http://www.scopus.com/inward/record.url?scp=85071294580&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071294580&partnerID=8YFLogxK

U2 - 10.1109/CEC.2019.8789932

DO - 10.1109/CEC.2019.8789932

M3 - Conference contribution

AN - SCOPUS:85071294580

T3 - 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings

SP - 838

EP - 844

BT - 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -