Market moves predictions using Retrieval-Augmented Generation (RAG) analysis of capital market expert opinions in social media

Dmitrii Gimmelberg (), Alexey Belinskiy, Alexey Belinskiy, Marta Głowacka, Marta Głowacka, Sergei Korotkii, Valentin Artamonov and Iveta Ludviga
Additional contact information
Dmitrii Gimmelberg: RISEBA University of Applied Sciences, Latvia
Alexey Belinskiy: RISEBA University of Applied Sciences, Latvia
Alexey Belinskiy: Aestima Research, SIA, Latvia
Marta Głowacka: Aestima Research, SIA, Latvia
Marta Głowacka: SBS Swiss Business School, Switzerland
Sergei Korotkii: Aestima Research, SIA, Latvia
Valentin Artamonov: Aestima Research, SIA, Latvia
Iveta Ludviga: Aestima Research, SIA, Latvia

Entrepreneurship and Sustainability Issues, 2025, vol. 13, issue 1, 175-188

Abstract: This study explores the predictive value of expert opinions from financial market media using Artificial Intelligence (AI), specifically, Retrieval-Augmented Generation (RAG) framework integrated with a Large Language Model (LLM). By analysing 3,877 YouTube videos spanning 12 months, the research categorised 4,808 expert opinions—either explicit or inferred—into directional market predictions (up, down, flat) for seven diversified financial assets. Results indicate that aggregated expert opinions correlate significantly with short-term market movements but lose predictive power for longer horizons. Explicit opinions demonstrated similar accuracy to inferred judgments, suggesting that LLMs effectively extract latent insights from unstructured data, enhancing accessibility and utility for retail investors. The study highlights the democratising potential of LLMs, providing timely and scalable analysis of vast datasets. However, challenges remain, such as understanding domain-specific nuances and speaker attribution within multimedia content. Statistical analysis reveals that expert opinions, particularly when aggregated, identify exploitable inefficiencies, thereby challenging the Efficient Market Hypothesis's assumption of perfect information dissemination. Short-term market anomalies observed align with behavioural finance theories of cognitive bias and delayed information diffusion. By bridging qualitative sentiment with quantitative modelling, this research underscores the transformative role of AI-driven tools in financial analysis, offering new avenues for individual and institutional investors. Further development of LLMs tailored to domain-specific complexities may revolutionise investment practices and advance research on market behaviour.

Keywords: AI; RAG; LLM; market movement prediction; investment; social media; financial markets (search for similar items in EconPapers)
JEL-codes: C45 G11 G14 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://jssidoi.org/jesi/uploads/articles/49/Gimme ... _in_social_media.pdf (application/pdf)
https://jssidoi.org/jesi/article/1337 (text/html)

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:ssi:jouesi:v:13:y:2025:i:1:p:175-188

DOI: 10.9770/w9365778559

Access Statistics for this article

Entrepreneurship and Sustainability Issues is currently edited by Manuela Tvaronaviciene

More articles in Entrepreneurship and Sustainability Issues from VsI Entrepreneurship and Sustainability Center
Bibliographic data for series maintained by Manuela Tvaronaviciene ().