Learning Foreign Investors’ Trading Strategies with Artificial Neural Networks

Aekkachai Nittayagasetwat and Jiroj Buranasiri ()
Additional contact information
Aekkachai Nittayagasetwat: NIDA Business School, National Institute of Development Administration, College of Innovation, Thammasat University
Jiroj Buranasiri: Prachan Road, Phra Barom Maha Ratchawang, Phra Nakhon

A chapter in Business and Sustainable Development in a Globalized and Digitalized Era, 2026, pp 161-182 from Springer

Abstract: Abstract The increasing integration of foreign investor trading activity into emerging stock markets has positioned foreign investors as significant players influencing stock market returns and volatility, particularly in the Stock Exchange of Thailand (SET). This study applies artificial neural networks (ANNs) to investigate foreign trading strategies on the Stock Exchange of Thailand and compares the performance of the ANN model with the traditional ordinary least squares (OLS) regression model. The dataset, obtained from LSEG Datastream, spans from the introduction of quantitative easing monetary policy in 2009 to March 2025. The analysis incorporates a set of control variables, including SET index variables (returns, volumes, and volatilities) as well as the USD/THB exchange rate, all of which are publicly available. Empirical results demonstrate that the ANN, an application of artificial intelligence (AI), outperforms OLS, a traditional econometric approach. The ANN model’s coefficient of determination (R-squared) is higher than that of OLS. For predicting foreign investors’ trading decisions to “buy” and “not buy,” the ANN model developed in this study achieves a prediction accuracy of approximately 65%, with the costly Type I error—wrongly classifying a “sell” (or “not buy”) strategy as a “buy” strategy—around 15%.

Keywords: artificial intelligence; artificial neural network; ordinary least squares; emerging stock market; foreign investors; the Stock Exchange of Thailand; stock market return; stock market turnover; Parkinson volatility; Pearson correlation. (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:prbchp:978-3-032-29346-6_9

Ordering information: This item can be ordered from
http://www.springer.com/9783032293466

DOI: 10.1007/978-3-032-29346-6_9

Access Statistics for this chapter

More chapters in Springer Proceedings in Business and Economics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().