Foreign Exchange Prediction using Decision Tree Algorithm: A Machine Learning Approach
DOI:
https://doi.org/10.62054/ijdm/0104.20Ключевые слова:
Decision tree, Forex, Machine Learning, Predictions, Technical AnalysisАннотация
The study used decision tree algorithm of machine learning to design a tool for predicting foreign exchange to help traders make well-informed trading decisions. The processes involve data analysis, preprocessing, model design, validation, and programming integration. The model was created using Python programming language in Jupita-Note to predict the forex market based on the FOREXTIME Meta Trader 4 dataset and applied preprocessing techniques for data normalization. Stochastic oscillator and Linear Weighted Moving average indicators were incorporated. It used historical data obtained from FOREXTIME for the decision tree. A predictive model utilizing a decision tree algorithm was designed to leverage these indicators for accurate forecasting. Evaluation metric techniques were employed to assess and evaluate the model's performance and reliability. The historical data gathered covered the years 2018 through 2023. The accuracy of the model was found to be 98%. This has shown the usefulness of decision trees in forex predictions. At implementation, Meta Quote Language 4 was used. Twenty transactions were executed based on the signal generated by the system over various time frames and currency pairs; 13 (65%) of the transactions were profitable, while 7 (35%) recorded loss. This practical implementation shows the applicability of the research findings in real-world trading scenarios. The achieved results underline the potential of combining machine learning and technical indicators to enhance trading decisions.
Библиографические ссылки
Abid-Althaqafi, N. R., and Alsalamah, H. A. (2024). The Effect of Feature Selection on the Accuracy of X-Platform User Credibility Detection with Supervised Machine Learning. Electronics, 13(1), 205.
Afzal, M. and Bushra H. (2013). Factors Influencing Real Exchange Rate: International Evidence. International Journal of Finance. 2013, Vol. 25 Issue 4, p7946-7965. 20p. Retrieved September 14, 2022.
Alamili, M. (2011). Exchange Rate Prediction Using Support Vector Machines: a Comparison with Artificial Neural Networks. A Master Thesis Submitted to the Faculty of Technology, Policy and Management Section of Information and Communication Technology, Delft University of Technology.
Bank for International Settlements. (2022). Triennial Central Bank Survey of Foreign Exchange and Over- the-Counter Derivatives Markets in 2022. Retrieved April14, 2023.
Barzykin, A., P. Bergault, O. Gueant, (2021). Market making by an FX dealer: tiers, pricing ladders and hedging rates for optimal risk control. Preprint arXiv:2112.02269, arXiv.
Botsvadze, I. (2018). IOSR Journal of Applied Geology and Geophysics (IOSR-JAGG) e-ISSN: 2321 – 0990, p-ISSN: 2321 – 0982.6(3) Ver.I (May. – June.2018), PP 61-68www.iosrjournals.org DOI: 10.9790/0990-0603016168
Brown, T., Johnson, A., and Lee, C. (2001). "The impact of monetary policy on currency exchange rates: A
fundamental analysis approach." Journal of Financial Economics, 48(2), 157-178.
Charbuty, B. and Abdulazeez, A (2021). “Classification Based on Decision Tree Algorithm for Machine Learning”, JASTT, 2(1): 20 - 28, Mar. 2021.
Cohen, G. (2022). Algorithmic Trading and Financial Forecasting Using Advanced Artificial Intelligence Methodologies. Mathematics, 10(18), 3302. MDPI AG.
Da, Z., and Halim, S. (2024). Prediction of bullish and bearish candlestick signals movement on forex using random forest and multilayer perceptron. In AIP Conference Proceedings (Vol. 2951, No. 1). AIP Publishing
Doe, J. S., Tuffour, J. K., and Tuffour, M. K. (2019). Fisher Effect and Commercial Banks’ lending Rates.
Flassbeck, H, and Marca L. M (2007). Global imbalances and destabilizing speculation Trade and development report 2007 (Chapter IB).
Investopedia, (2022). Foreign Exchange Reasons for traders www.investoedia.conr/articles/FOREX/10/top-reasons- FOREX-traders-fail.asp (accessed 27th December, 2022)
Investopedia, (2023). Foreign Exchange Terms. www.investopedia.com/terms/f/foreign-exchange.asp (Accessed
th March, 2023)
Lee, C., and Wang, Y. (2013). "Economic data releases and their impact on currency orecasting: A fundamental analysis study." Journal of Economic Research
Nelson, D. M. Q., Pereira, A. C. M. and de Oliveira, R.A, (2017) "Stock market's price
movement prediction with LSTM neural networks," 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA, 2017, pp. 1419-1426, Doi: 10.1109/IJCNN.2017.7966019.
Nison, S. (2021). Candlestick Charting Basics: Spotting the Early Reversals for Maximum Profits (3rd ed.). John Wiley and Sons.
Record, N. (2014). Currency Overlay (Wiley Finance Series)
Rokach, Lior and Maimon, O. (2008). Data mining with decision trees: theory and applications. World Scientific Pub Co Inc. ISBN 978-9812771711.
Shakoor, D. M., Maihami, V., and Maihami, R. (2021). A machine learning recommender system based on collaborative filtering using Gaussian mixture model clustering. Mathematical Methods in the Applied Sciences.
Svitlana, G., (2016). Neural networks performance in exchange rate prediction,
Neurocomputing, Volume 172, Pages 446-452,
ISSN 0925 2312,
Tay, F. E., and Cao, L. (2021). Support vector machines. In F. E. Tay and C. M. Tay (Eds.), Machine learning for predictive analytics (pp. 147-164). Springer.
Zhang, Y., Jin, Z., Blumenstein, M. (eds) Knowledge Science, Engineering and
Management. SEM 2017. Lecture Notes in Computer Science (), vol 10412.
Springer, Cham. https://doi.org/10.1007/978-3-319-63558-3_4
Загрузки
Опубликован
Заявление о доступности данных
Not available yet but will soon be available.
Выпуск
Раздел
Лицензия
Copyright (c) 2024 International Journal of Development Mathematics (IJDM)
Это произведение доступно по лицензии Creative Commons «Attribution» («Атрибуция») 4.0 Всемирная.
Authors are solely responsible for obtaining permission to reproduce any copyrighted material contained in the manuscript as submitted. Any instance of possible prior publication in any form must be disclosed at the time the manuscript is submitted and a
copy or link to the publication must be provided.
The Journal articles are open access and are distributed under the terms of the Creative
Commons Attribution-NonCommercial-NoDerivs 4.0 IGO License, which permits use,
distribution, and reproduction in any medium, provided the original work is properly cited.
No modifications or commercial use of the articles are permitted.
