Short-term Price Prediction in Initial Public Offerings Using XGBoost: Bist Technology Sector Example

Gazme Şekeroğlu and Ayşe Merve Acılar

Journal of Research in Economics, Politics & Finance, 2025, vol. 10, issue 2, 549-567

Abstract: The aim of the study is to predict the closing price of the next trading day's stocks, of the initial public offering firms in the short term (between 5 and 10 days). For this purpose, firstly, the companies that went public in BIST in 2022, 2023, and 2024 are listed. Among these sectors, the decision was made to conduct the research in the technology sector, which experienced the highest number of initial public offerings in 2024. Using the model created with the XGBoost algorithm, price prediction for the Borsa Istanbul technology sector was made. The data to be used in the analyses consist of the daily closing stock prices of FORTE, which was the first IPO in 2023 and operates in the technology sector, from 15.06.2023 to 28.06.2024. It also includes the daily closing values of the BIST TECHNOLOGY and BIST IPO indices, and the first four-day closing stock prices of the technology sector companies (ODINE, PATEK, and ALTNY) that were the first IPOs in 2024. As a result of the coding steps performed using Python, it was found that the difference between the predicted prices and the actual prices gradually decreased from the fifth to the tenth day after the IPO.

Keywords: Initial Public Offering; Stock Price Prediction; XGboost Algorithm (search for similar items in EconPapers)
JEL-codes: E27 E44 O16 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://dergipark.org.tr/tr/download/article-file/4533149 (application/pdf)

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:ahs:journl:v:10:y:2025:i:2:p:549-567

DOI: 10.30784/epfad.1622717

Access Statistics for this article

More articles in Journal of Research in Economics, Politics & Finance from Ersan ERSOY
Bibliographic data for series maintained by Ersan Ersoy ().