Please use this identifier to cite or link to this item:
Title: Financial Forecasting using Deep Learning with an Optimized Trading Strategy
Authors: Maratkhan, A.
İlyassov, I.
Aitzhanov, M.
Demirci, Muhammed Fatih
Özbayoğlu, Ahmet Murat
Keywords: Financial forecasting
time-series classification
deep learning
convolutional neural networks
cuckoo search
Issue Date: 2019
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source: Maratkhan, A., Ilyassov, I., Aitzhanov, M., Demirci, M. F., and Ozbayoglu, M. (2019, June). Financial Forecasting using Deep Learning with an Optimized Trading Strategy. In 2019 IEEE Congress on Evolutionary Computation (CEC) (pp. 838-844). IEEE.
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. © 2019 IEEE.
Description: 2019 IEEE Congress on Evolutionary Computation ( 2019: Wellington; New Zealand)
ISBN: 9.78173E+12
Appears in Collections:Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Show full item record

CORE Recommender


checked on Sep 23, 2022

Page view(s)

checked on Dec 26, 2022

Google ScholarTM



Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.