Akademik Veri Yönetim Sistemi
SN Business and Economics, cilt.5, sa.12, 2025 (Scopus)
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.