Artificial intelligence in behavioral finance: a global review of cognitive bias modeling in investor decision-making

Şadi Evren Şeker (), Başak Turan İçke, Serhat Yanık, İbrahim Sırma, Mehmet Akif İçke and Ece Kozol ()
Additional contact information
Şadi Evren Şeker: Istanbul University, Faculty of Computer and Information Technologies
Başak Turan İçke: Istanbul University, Faculty of Political Sciences
Serhat Yanık: Istanbul University, Faculty of Political Sciences
İbrahim Sırma: Istanbul University, Faculty of Political Sciences
Mehmet Akif İçke: Istanbul University, Faculty of Political Sciences
Ece Kozol: Istanbul University, Faculty of Political Sciences

SN Business & Economics, 2025, vol. 5, issue 12, 1-30

Abstract: Abstract Artificial intelligence (AI) is increasingly transforming behavioral finance research by enabling the real-time extraction of investor behavioral patterns from large-scale data sources. This expanded literature review surveys over a decade of scholarly work on how advanced AI algorithms – including deep learning, natural language processing (NLP), explainable AI (XAI), graph neural networks (GNNs), and clustering methods – are used to detect cognitive biases and gauge market psychology in financial decision-making. We retain the original review structure, beginning with foundational theories of behavioral finance and moving through thematic sections organized by specific biases (overconfidence, herding and social proof, prospect theory-related biases, and availability heuristic) and data types (social media, news, trading records, etc.). Recent studies from 2015 to 2025 are emphasized, highlighting global contributions from the Americas, Europe, and Asia. We find that AI techniques have been applied to identify classic biases – such as overconfident trading, herd behavior driven by social influence, loss-aversion effects, and attention-driven market moves – with unprecedented granularity and timeliness. Social media posts, news feeds, and brokerage trading data can be mined for sentiment and anomalies that serve as early-warning signals of investor sentiment shifts or bias-driven market excesses. Comparative analysis suggests that while deep learning models often achieve high predictive power in modeling complex behavioral signals, their opacity calls for XAI methods to ensure interpretability and trust. We conclude by discussing future directions, including the integration of multi-source data and hybrid models, improvements in explainability, and ethical considerations. The goal is a rigorous yet accessible synthesis suitable for a high-impact journal, demonstrating how AI advances are elevating behavioral finance into a data-driven, real-time discipline with practical implications for market monitoring and investor decision support.

Keywords: Behavioural finance; Cognitive biases; Artificial intelligence; Explainable AI; Investor sentiment; Market psychology (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s43546-025-00986-6 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:snbeco:v:5:y:2025:i:12:d:10.1007_s43546-025-00986-6

Ordering information: This journal article can be ordered from
https://www.springer.com/journal/43546

DOI: 10.1007/s43546-025-00986-6

Access Statistics for this article

SN Business & Economics is currently edited by Gino D'Oca

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