Predicting stock returns: ARMAX vs. machine learning

dc.contributor.authorLapitskaya, Darya
dc.contributor.authorEratalay, Hakan
dc.contributor.authorRajesh Sharma
dc.date.accessioned2022-03-23T16:26:54Z
dc.date.available2022-03-23T16:26:54Z
dc.date.issued2022
dc.description.abstractIn the modern world, online social and news media significantly impact society, economy, and financial markets. In this chapter, we compared the predictive performance of financial econometrics and machine learning and deep learning methods for the returns of the stocks of the SP100 index. The analysis is enriched by using COVID-19 related news sentiments data collected for a period of 10 months. We analyzed the performance of each model and found the best algorithm for such types of predictions. For the sample we analyzed, our results indicate that the autoregressive moving average model with exogenous variables (ARMAX) has a comparable predictive performance to the machine and deep learning models, only outperformed by the extreme gradient boosted trees (XGBoost) approach. This result holds both in the training and testing datasets.en
dc.identifier.urihttps://doi.org/10.1007/978-3-030-85254-2_27
dc.identifier.urihttp://hdl.handle.net/10062/77682
dc.language.isoengen
dc.relationinfo:eu-repo/grantAgreement/EC/H2020/822781///GROWINPROen
dc.rightsinfo:eu-repo/semantics/openAccessen
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectsentiment analysisen
dc.subjectmachine learningen
dc.subjectARMAXen
dc.subjectstock returns predictionen
dc.subjectdeep learningen
dc.subjectCOVID-19en
dc.titlePredicting stock returns: ARMAX vs. machine learningen
dc.typeinfo:eu-repo/semantics/articleen

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Lapitskaya_Eratalay_Sharma_2022.pdf
Size:
355.18 KB
Format:
Adobe Portable Document Format
Description:

License bundle

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