Are machine learning models effective in predicting emerging markets? Investigating the accuracy of predictions in emerging stock market indices

Namitha Yeldho, Dany Thomas, Vimal George Kurian, Chandralekha Arathy and Ajithakumari Vijayappan Nair Biju ()
Additional contact information
Namitha Yeldho: University of Kerala
Dany Thomas: University of Kerala
Vimal George Kurian: CMS College Kottayam
Chandralekha Arathy: University of Kerala
Ajithakumari Vijayappan Nair Biju: University of Kerala

Quality & Quantity: International Journal of Methodology, 2025, vol. 59, issue 1, No 35, 839-904

Abstract: Abstract The Indian stock market is an emerging market that has outperformed other significant markets like the US, UK, and Japan, providing a return of 19 percent, the highest in the world. With the exponential growth prospects of the market, we combine big data and deep learning methods to predict the market and produce accurate market predictions of emerging market indices. We investigated the stock prediction accuracy using Bidirectional Long short-term memory (LSTM) models using Python programming in the emerging stock market indices like NIFTY 50 and NIFTY 100. A recurrent neural network for sequence modelling tasks was employed to predict the stock price movements using data on NIFTY 50 and NIFTY 100 from 2011 to 2023. Performance matrices Root Mean Square Error (RMSE), coefficient of determination (R2), Mean Absolute Percentage Error (MAPE) and Average Relative Variance (ARV) were employed for testing the model’s accuracy. While examining the accuracy of the prediction, results underscore that our model accurately predicts the emerging market indices; a specific model efficiently predicts a more stable but consistently growing market, NIFTY 50, than NIFTY 100, which is more volatile. Our findings show investors and policymakers that the Bidirectional LSTM model best predicts markets with lower price volatility. This paper is more novel in that it gives promising results while predicting stock prices in the bull market periods of NIFTY 50 and NIFTY 100.

Keywords: Stock prediction; Machine learning; Deep learning; Emerging market; Bidirectional Long short-term memory; BiLSTM (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11135-024-01964-0 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:qualqt:v:59:y:2025:i:1:d:10.1007_s11135-024-01964-0

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11135

DOI: 10.1007/s11135-024-01964-0

Access Statistics for this article

Quality & Quantity: International Journal of Methodology is currently edited by Vittorio Capecchi

More articles in Quality & Quantity: International Journal of Methodology from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().