Forecasting high‐frequency excess stock returns via data analytics and machine learning

buir.contributor.authorŞensoy, Ahmet
buir.contributor.orcidŞensoy, Ahmet|0000-0001-7967-5171
dc.citation.epage75en_US
dc.citation.issueNumber1
dc.citation.spage22
dc.citation.volumeNumber29
dc.contributor.authorAkyildirim, E.
dc.contributor.authorNguyen, D.K.
dc.contributor.authorŞensoy, Ahmet
dc.contributor.authorŠikić, M.
dc.date.accessioned2024-03-19T06:31:01Z
dc.date.available2024-03-19T06:31:01Z
dc.date.issued2023-01
dc.departmentDepartment of Management
dc.description.abstractBorsa Istanbul introduced data analytics to present additional information about its market conditions. We examine whether this product can be utilized via var ious machine learning methods to predict intraday excess returns. Accordingly, these analytics provide significant prediction ratios above 50% with ideal profit ratios that can reach up to 33%. Among all the methods considered, XGBoost (logistic regression) performs better in predicting excess returns in the long‐term analysis (short‐term analysis). Results provide evidence for the benefits of both the analytics and the machine learning methods and raise further discussion on the semistrong market efficiency.
dc.description.provenanceMade available in DSpace on 2024-03-19T06:31:01Z (GMT). No. of bitstreams: 1 Forecasting_high_frequency_excess_stock_returns_via_data_analytics_and_machine_learning.pdf: 3363608 bytes, checksum: 75b8d22b27d3dc38637374e374d4ffc3 (MD5) Previous issue date: 2023-01-01en
dc.identifier.doi10.1111/eufm.12345
dc.identifier.eissn1468-036X
dc.identifier.issn1354-7798
dc.identifier.urihttps://hdl.handle.net/11693/114926
dc.language.isoen
dc.publisherJohn Wiley and Sons Inc.
dc.relation.isversionofhttps://dx.doi.org/10.1111/eufm.12345
dc.rightsCC BY-NC-ND (Attribution-NonCommercial-NoDerivs 4.0 International)
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.source.titleEuropean Financial Management
dc.subjectBig data
dc.subjectData analytics
dc.subjectEfficient market hypothesis
dc.subjectForecasting
dc.subjectMachine learning
dc.titleForecasting high‐frequency excess stock returns via data analytics and machine learning
dc.typeArticle

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Forecasting_high_frequency_excess_stock_returns_via_data_analytics_and_machine_learning.pdf
Size:
3.21 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.01 KB
Format:
Item-specific license agreed upon to submission
Description: