USING OF ARTIFICIAL INTELLIGENCE-BASED LEARNING METHODS IN FINANCE: A BIBLIOMETRIC ANALYSIS

Erdi Bayram; Gökhan Berk Özbek

Article Details

USING OF ARTIFICIAL INTELLIGENCE-BASED LEARNING METHODS IN FINANCE: A BIBLIOMETRIC ANALYSIS

Authors:

Erdi Bayram | Gökhan Berk Özbek

Publisher:

Cukurova University

Main Topics:

Ekonometri (Diğer)

Journal:

Çukurova Üniversitesi Sosyal Bilimler Enstitüsü Dergisi Vol.34 Issue Uygarlığın Dönüşümü: Yapay Zekâ, pp.303-321

Document Type:

Article

Publication Date:

7/2025

Document Language:

Turkish

Document ID (Org No.):

2001348577

pISSN:

1304-8899

Keywords:

Abstract:

 The study presents a bibliometric analysis of research in finance focusing on machine learning, deep learning, and reinforcement learning. The analysis covers the period from 2001 to 2025 and includes only articles written in English and indexed in the Web of Science and Scopus databases. Using custom code in Rstudio environment, articles from both databases were merged, duplicates were removed, and a final dataset was prepared for analysis.The studies were examined bibliographically in terms of authors, journals, keywords, thematic areas, citation counts, and author affiliations. For visual analysis, the Biblioshiny software was used. The findings reveal a significant increase in the number of publications in this field, particularly after 2018. Key research themes identified include stock price prediction, volatility forecasting, sentiment analysis, neural networks, and optimization. The Journal Expert Systems with Applications was found to have the highest number of publications in the field. Researchers from the Peoples Republic of China contributed the largest share, accounting for 29.8 of all publications. The most frequently occurring terms in article titles include stock, learning, prediction, market, forecasting, analysis, sentiment, trading, and portfolio. This study is considered important for identifying the current state, academic impact, and future research directions of AI-based methods and models within the finance literature.

 The study presents a bibliometric analysis of research in finance focusing on machine learning, deep learning, and reinforcement learning. The analysis covers the period from 2001 to 2025 and includes only articles written in English and indexed in the Web of Science and Scopus databases. Using custom code in Rstudio environment, articles from both databases were merged, duplicates were removed, and a final dataset was prepared for analysis.The studies were examined bibliographically in terms of authors, journals, keywords, thematic areas, citation counts, and author affiliations. For visual analysis, the Biblioshiny software was used. The findings reveal a significant increase in the number of publications in this field, particularly after 2018. Key research themes identified include stock price prediction, volatility forecasting, sentiment analysis, neural networks, and optimization. The Journal Expert Systems with Applications was found to have the highest number of publications in the field. Researchers from the Peoples Republic of China contributed the largest share, accounting for 29.8 of all publications. The most frequently occurring terms in article titles include stock, learning, prediction, market, forecasting, analysis, sentiment, trading, and portfolio. This study is considered important for identifying the current state, academic impact, and future research directions of AI-based methods and models within the finance literature.

 The study presents a bibliometric analysis of research in finance focusing on machine learning, deep learning, and reinforcement learning. The analysis covers the period from 2001 to 2025 and includes only articles written in English and indexed in the Web of Science and Scopus databases. Using custom code in Rstudio environment, articles from both databases were merged, duplicates were removed, and a final dataset was prepared for analysis.The studies were examined bibliographically in terms of authors, journals, keywords, thematic areas, citation counts, and author affiliations. For visual analysis, the Biblioshiny software was used. The findings reveal a significant increase in the number of publications in this field, particularly after 2018. Key research themes identified include stock price prediction, volatility forecasting, sentiment analysis, neural networks, and optimization. The Journal Expert Systems with Applications was found to have the highest number of publications in the field. Researchers from the Peoples Republic of China contributed the largest share, accounting for 29.8 of all publications. The most frequently occurring terms in article titles include stock, learning, prediction, market, forecasting, analysis, sentiment, trading, and portfolio. This study is considered important for identifying the current state, academic impact, and future research directions of AI-based methods and models within the finance literature.

 Çalışmada Makine Öğrenimi, Derin Öğrenme ve Pekiştirmeli Öğrenme ile ilgili finans alanındaki çalışmaların bibliyometrik incelemesi yapılmıştır. 2001-2025 periyodunu kapsayan araştırmada, Web of Science ve Scopus veri tabanlarında indekslenen, İngilizce yazılmış, yalnızca makale türündeki çalışmalar analiz edilmiştir. Her iki veri tabanındaki çalışmalar Rstudio ortamında özel bir kod dizini kullanılarak birleştirilmiş, tekrarlayanlar ayıklanmış ve tek bir veri setiyle çalışılmıştır. Çalışmalar yazar, dergi, anahtar kelimeler, tematik konular, atıf sayıları ve yazar ülkeleri bağlamında bibliyografik olarak araştırılmıştır. Çalışmaların görsel analizinde ise Biblioshiny programından yararlanılmıştır. Bu araştırmanın sonuçları olarak ilgili alandaki yayın sayısında özellikle 2018 sonrası ciddi bir artış olduğu izlenmektedir. Pay senedi fiyat tahminlemesi, volatilite öngörümlemesi, duygu analizi, sinir ağları ve optimizasyon gibi konuların ilgili alandaki temel temaları oluşturduğu tespit edilmiştir. En fazla yayının Expert Systems with Applications dergisinde yer aldığı ve Çin Halk Cumhuriyetinden araştırmacıların 29,8lik bir oranla ilgili alanlarda en yüksek yayın üretme oranına sahip olduğu görülmektedir. Çalışılan veri setinde yer alan çalışmaların başlıklarında geçen en yaygın kelimeler ise pay senedi, öğrenme, tahmin, piyasa, öngörümleme, analiz, duygu, alım-satım ve portföydür. Araştırmanın yapay zekanın ilgili alt disiplinlerine dayalı modellerin finans literatürü açısından mevcut durumunu, etkisini ve potansiyel araştırma konularını ortaya koyması bakımından önemli olduğu olduğu düşünülmektedir.

Article Details

USING OF ARTIFICIAL INTELLIGENCE-BASED LEARNING METHODS IN FINANCE: A BIBLIOMETRIC ANALYSIS

Authors:

Erdi Bayram | Gökhan Berk Özbek

Publisher:

Cukurova University

Main Topics:

Ekonometri (Diğer)

Journal:

Çukurova Üniversitesi Sosyal Bilimler Enstitüsü Dergisi Vol.34 Issue Uygarlığın Dönüşümü: Yapay Zekâ, pp.303-321

Document Type:

Article

Publication Date:

7/2025

Document Language:

Turkish

Document ID (Org No.):

2001348577

pISSN:

1304-8899

Machine Learning

Deep Learning

Reinforcement Learning

Bibliometric Analysis

Quantitative FinanceMakine Öğrenimi

Derin Öğrenme

Pekiştirmeli Öğrenme

Bibliyometrik Analiz

Kantitatif Finans

Issues

Article Details

Authors: Erdi Bayram | Gökhan Berk Özbek

Publisher: Cukurova University

Main Topics: Ekonometri (Diğer)

Journal: Çukurova Üniversitesi Sosyal Bilimler Enstitüsü Dergisi Vol.34 Issue Uygarlığın Dönüşümü: Yapay Zekâ, pp.303-321

Document Type: Article

Publication Date: 7/2025

Document Language: Turkish

Document ID (Org No.): 2001348577

pISSN: 1304-8899

Issues

Authors:

Erdi Bayram | Gökhan Berk Özbek

Publisher:

Cukurova University

Main Topics:

Ekonometri (Diğer)

Journal:

Çukurova Üniversitesi Sosyal Bilimler Enstitüsü Dergisi Vol.34 Issue Uygarlığın Dönüşümü: Yapay Zekâ, pp.303-321

Document Type:

Article

Publication Date:

7/2025

Document Language:

Turkish

Document ID (Org No.):

2001348577

pISSN:

1304-8899