Machine learning-based forecasting of significant daily returns in foreign exchange markets

Simple item page
dc.contributor.authorKamalov, Firuz
dc.contributor.authorGurrib, Ikhlaas
dc.date.accessioned2022-12-22T12:57:36Z
dc.date.available2022-12-22T12:57:36Z
dc.date.copyright© 2022
dc.date.issued2022
dc.description.abstractFinancial forecasting has always attracted an enormous amount of interest among researchers in quantitative analysis. The advent of modern machine learning models has introduced new tools to tackle this classical problem. In this paper, we apply machine learning algorithms to a hitherto unexplored question of forecasting instances of significant fluctuations in currency exchange rates. We carry out an extensive comparative study of ten modern machine learning methods. In our experiments, we use data on four major currency pairs over a 20-year period. A key contribution is the novel use of outlier detection methods for this purpose. Numerical experiments show that outlier detection methods substantially outperform traditional machine learning and finance techniques. In addition, we show that a recently proposed new outlier detection method PKDE produces the best overall results. Our findings hold across different currency pairs, significance levels, and time horizons indicating the robustness of the proposed method. Copyright © 2022 Inderscience Enterprises Ltd.
dc.identifier.citationKamalov, F., & Gurrib, I. (2022). Machine learning-based forecasting of significant daily returns in foreign exchange markets. International Journal of Business Intelligence and Data Mining, 21(4), 465-483. doi:10.1504/ijbidm.2022.126505
dc.identifier.issn17438187
dc.identifier.urihttps://doi.org/10.1504/IJBIDM.2022.126505
dc.identifier.urihttps://hdl.handle.net/20.500.12519/738
dc.language.isoen_US
dc.publisherInderscience Publishers
dc.relationAuthors Affiliations :Kamalov, F., Faculty of Engineering, Canadian University Dubai, Dubai, United Arab Emirates; Gurrib, I., Faculty of Engineering, Canadian University Dubai, Dubai, United Arab Emirates
dc.relation.ispartofseriesInternational Journal of Business Intelligence and Data Mining; Volume 21, Issue 4
dc.rightsPermission to reuse abstract has been secured from Inderscience Publishers.
dc.rights.holderCopyright : © 2022 Inderscience Enterprises Ltd.
dc.subjectforecasting
dc.subjectforeign exchange
dc.subjectKDE
dc.subjectkernel density estimation
dc.subjectmachine learning
dc.subjectneural networks
dc.subjectoutlier detection
dc.subjecttail events
dc.titleMachine learning-based forecasting of significant daily returns in foreign exchange markets
dc.typeArticle

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Access Instruction 738.pdf
Size:
43.93 KB
Format:
Adobe Portable Document Format
Description:
Download

Collections

Department of Electrical Engineering