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

Akyildirim, Erdinc; Nguyen, Duc Khuong; Sensoy, Ahmet; Šikić, Mario

Abstract

Borsa Istanbul introduced data analytics to present additional information about its market conditions. We examine whether this product can be utilized via various 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 semi-strong market efficiency.

Citation

Akyildirim, E., Nguyen, D. K., Sensoy, A., & Šikić, M. (2023). Forecasting high-frequency excess stock returns via data analytics and machine learning. European Financial Management, 29(1), 22-75. https://doi.org/10.1111/eufm.12345

• Journal Article Type: Article
• Acceptance Date: Nov 18, 2021
• Online Publication Date: Dec 7, 2021
• Publication Date: 2023-03
• Deposit Date: Oct 24, 2024
• Publicly Available Date: Oct 25, 2024
• Print ISSN: 1354-7798
• Electronic ISSN: 1468-036X
• Publisher: Wiley
• Peer Reviewed: Peer Reviewed
• Volume: 29
• Issue: 1
• Pages: 22-75
• DOI: https://doi.org/10.1111/eufm.12345
• Keywords: Big data; data analytics; machine learning; forecasting; efficient market hypothesis JEL: C52; C53; D81; G14; G17
• Public URL: https://nottingham-repository.worktribe.com/output/40865295
• Publisher URL: https://onlinelibrary.wiley.com/doi/10.1111/eufm.12345