Received:
2025-03-11 | Accepted:
2025-07-04 | Published:
2025-09-30
Title
Market moves predictions using Retrieval-Augmented Generation (RAG) analysis of capital market expert opinions in social media
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
Artificial Intelligence (AI), RAG, LLM, market movement prediction, investment, social media, financial markets
JEL classifications
G11
, G14
, C45
URI
http://jssidoi.org/jesi/article/1337
DOI
Pages
175-188
Funding
This is an open access issue and all published articles are licensed under a
Creative Commons Attribution 4.0 International License
References
Arisoma, D.S., & Narulita, L.F. (2019). System Design and Development of Financial Product Sales Forecasting with exponentially weighted moving average and exponential smoothing method, Proceeding UII-ICABE, pp. 1-6. https://journal.uii.ac.id/icabe/article/view/14681
Search via ReFindit
Baltakienė, M., Kanniainen, J., & Baltakys, K. (2021). Identification of information networks in stock markets. Journal of Economic Dynamics and Control, 131, p. 104217. https://doi.org/10.1016/j.jedc.2021.104217
Search via ReFindit
Barberis, N., Shleifer, A., & Vishny, R. (1998). A model of investor sentiment1. Journal of Financial Economics, 49(3), pp. 307-343. 00027-0 https://doi.org/10.1016/S0304-405X(98)
Search via ReFindit
Bender, S. et al. (2022). Millionaires speak: What drives their personal investment decisions? Journal of Financial Economics, 146(1), pp. 305-330. https://doi.org/10.1016/j.jfineco.2021.09.016
Search via ReFindit
Billah, M.M. et al. (2024). Stock price prediction: comparison of different moving average techniques using deep learning model. Neural Computing and Applications, 36(11), pp. 5861-5871. https://doi.org/10.1007/s00521-023-09369-0
Search via ReFindit
Birhane, A., & McGann, M. (2024). Large Models of What? Mistaking Engineering Achievements for Human Linguistic Agency. Language Sciences, 106, 101672 https://doi.org/10.1016/j.langsci.2024.101672
Search via ReFindit
Blasco, N., Corredor, P., & Ferreruela, S. (2012). Market sentiment: a key factor of investors’ imitative behaviour. Accounting & Finance, 52(3), pp. 663–689. https://doi.org/10.1111/j.1467-629X.2011.00412.x
Search via ReFindit
Bowman, S.R. (2023). Eight Things to Know about Large Language Models. Critical AI, 2 (2). https://doi.org/10.1215/2834703X-11556011
Search via ReFindit
Cao, H. (2024). Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark. Conference ’XX, June 03–05, 2024, Woodstock, NY. arXiv. https://doi.org/10.48550/arXiv.2406.01607
Search via ReFindit
Cao, Y. et al. (2024). ECC Analyzer: Extract Trading Signal from Earnings Conference Calls using Large Language Model for Stock Performance Prediction. Conference ’XX, June 03–05, 2024, Woodstock, NY. arXiv. https://doi.org/10.48550/arXiv.2404.18470
Search via ReFindit
Chaitanya, D.B., & Nordin, N. (2021). The Relationship between Psychological Factors, Risk Perception and Social Media on Investment Decision Making. International Journal of Advanced Research in Economics and Finance, 3(4), pp. 55-72. https://myjms.mohe.gov.my/index.php/ijaref/article/view/16350
Search via ReFindit
Chandra, A., & Kumar, R. (2011). Factors Influencing Indian Individual Investor Behaviour: Survey Evidence. Rochester, NY. https://doi.org/10.2139/ssrn.2029642
Search via ReFindit
Cheema, A.K., Ding, W., & Wang, Q. (2023). The cross-section of January effect. Journal of Asset Management, 24(6), pp. 513-530. https://doi.org/10.1057/s41260-023-00324-1
Search via ReFindit
Chordia, T., Roll, R., & Subrahmanyam, A. (2005). Evidence on the speed of convergence to market efficiency. Journal of Financial Economics, 76(2), pp. 271-292. https://doi.org/10.1016/j.jfineco.2004.06.004
Search via ReFindit
Clare, A. et al. (2016). The trend is our friend: Risk parity, momentum and trend following in global asset allocation. Journal of Behavioral and Experimental Finance, 9, pp. 63-80. https://doi.org/10.1016/j.jbef.2016.01.002
Search via ReFindit
De Bondt, W.F.M., & Thaler, R. (1985). Does the Stock Market Overreact? The Journal of Finance, 40(3), pp. 793-805. https://doi.org/10.1111/j.1540-6261.1985.tb05004.x
Search via ReFindit
Delgadillo, J., Kinyua, J., & Mutigwe, C. (2024). FinSoSent: Advancing Financial Market Sentiment Analysis through Pretrained Large Language Models. Big Data and Cognitive Computing, 8(8), p. 87. https://doi.org/10.3390/bdcc8080087
Search via ReFindit
Droke, C. (2001). Moving Averages Simplified’, USA: Marketplace Books., 96. https://www.amazon.com/Moving-Averages-Simplified-Clif-Droke/dp/1883272661
Search via ReFindit
Edwards, R.D., Magee, J., & Bassetti, W.C. (2018) Technical analysis of stock trends. CRC press. https://www.taylorfrancis.com/books/mono/10.4324/9781315115719/technical-analysis-stock-trends-bassetti-robert-edwards-john-magee
Search via ReFindit
Fama, E.F. (1970). Efficient Capital Markets: A Review of Theory and Empirical Work. Journal of Finance, 25(2), pp. 383-417. https://doi.org/10.2307/2325486
Search via ReFindit
Fama, E.F., & French, K.R. (1992). The Cross-Section of Expected Stock Returns. The Journal of Finance, 47(2), pp. 427-465. https://doi.org/10.1111/j.1540-6261.1992.tb04398.x
Search via ReFindit
Fama, E.F., & French, K.R. (2015). A five-factor asset pricing model. Journal of Financial Economics, 116(1), pp. 1-22. https://doi.org/10.1016/j.jfineco.2014.10.010
Search via ReFindit
Gaikwad, S.B. et al. (2023). Role of Social Media Information in Influencing Investment Preferences of Retail Investors: An Empirical Study. Journal of Informatics Education and Research, 3(2). https://doi.org/10.52783/jier.v3i2.381
Search via ReFindit
Gao, Y. et al. (2024). Retrieval-Augmented Generation for Large Language Models: A Survey’. arXiv. http://arxiv.org/abs/2312.10997
Search via ReFindit
Gayed, M.A. (2015). Lumber: Worth It’s Weight in Gold: Offense and Defense in Active Portfolio Management. SSRN Electronic Journal https://doi.org/10.2139/ssrn.2604248
Search via ReFindit
Goetzmann, W.N., & Kumar, A. (2001). Equity Portfolio Diversification. National Bureau of Economic Research http://www.nber.org/papers/w8686
Search via ReFindit
Grossman, S.J., & Stiglitz, J.E. (1980). On the Impossibility of Informationally Efficient Markets. The American Economic Review, 70(3), pp. 393–408.
Search via ReFindit
Gu, W. et al. (2024). Predicting Stock Prices with FinBERT-LSTM: Integrating News Sentiment Analysis. Proceedings of the 2024 8th International Conference on Cloud and Big Data Computing, pp. 67-72. https://doi.org/10.1145/3694860.3694870
Search via ReFindit
Harris, N., Butani, A., & Hashmy, S. (2024). Enhancing Embedding Performance through Large Language Model-based Text Enrichment and Rewriting. Advances in Artificial Intelligence and Machine Learning Research 4(2) 2358-2368. arXiv. https://doi.org/10.48550/arXiv.2404.12283
Search via ReFindit
Heydarian, P., Bifet, A., & Corbet, S. (2025). Understanding market sentiment analysis: A survey. Journal of Economic Surveys, 39(3), 1125-1147. https://doi.org/10.1111/joes.12645
Search via ReFindit
Hong, H., & Stein, J.C. (1999). A Unified Theory of Underreaction, Momentum Trading, and Overreaction in Asset Markets. The Journal of Finance, 54(6), pp. 2143-2184. https://doi.org/10.1111/0022-1082.00184
Search via ReFindit
Jegadeesh, N., & Titman, S. (1993). Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency. The Journal of Finance, 48(1), pp. 65-91. https://doi.org/10.1111/j.1540-6261.1993.tb04702.x
Search via ReFindit
Kacperczyk, M., Sialm, C., & Zheng, L. (2005). On the Industry Concentration of Actively Managed Equity Mutual Funds. The Journal of Finance, 60(4), pp. 1983-2011. https://doi.org/10.1111/j.1540-6261.2005.00785.x
Search via ReFindit
Koumou, G.B. (2020). Diversification and portfolio theory: a review. Financial Markets and Portfolio Management, 34(3), pp. 267-312. https://doi.org/10.1007/s11408-020-00352-6
Search via ReFindit
Krause, D. (2023). Proper Generative AI Prompting for Financial Analysis’. Rochester, NY: Social Science Research Network. https://doi.org/10.2139/ssrn.4453664
Search via ReFindit
Lorig, M., Zhou, Z., & Zou, B. (2019). A Mathematical Analysis of Technical Analysis. Applied Mathematical Finance, 26(1), pp. 38-68. https://doi.org/10.48550/arXiv.1710.09476
Search via ReFindit
Nguyen, D.S., Hoang, T.H.V., Pho, K.H., & Nhan, D.T. (2023). Financial Literacy and portfolio diversification: Evidence from Vietnam. Journal of Competitiveness, 15(3), 79-103. https://doi.org/10.7441/joc.2023.03.05
Search via ReFindit
Petukhova, A., Matos-Carvalho, J.P., & Fachada, N. (2024). Text clustering with LLM embeddings. International Journal of Cognitive Computing in Engineering, 6, 100-108. https://doi.org/10.1016/j.ijcce.2024.11.004
Search via ReFindit
Raudys, A., & Pabarškaitė, Ž. (2018). Optimising The Smoothness and Accuracy of Moving Average for Stock Price Data. Technological and Economic Development of Economy, 24(3), pp. 984-1003. https://doi.org/10.3846/20294913.2016.1216906
Search via ReFindit
Shiller, R.J. (2003). From Efficient Markets Theory to Behavioral Finance. Journal of Economic Perspectives, 17(1), pp. 83-104. https://doi.org/10.1257/089533003321164967
Search via ReFindit
Tetlock, P.C. (2007). Giving Content to Investor Sentiment: The Role of Media in the Stock Market. The Journal of Finance, 62(3), pp. 1139-1168. https://doi.org/10.1111/j.1540-6261.2007.01232.x
Search via ReFindit
Upson, R.B., Jessup, P.F., & Matsumoto, K. (1975). Portfolio Diversification Strategies. Financial Analysts Journal. https://doi.org/10.2469/faj.v31.n3.86
Search via ReFindit
Vamossy, D.F. (2024). Social Media Emotions and Market Behavior. arXiv. https://doi.org/10.48550/arXiv.2404.03792
Search via ReFindit
Wang, J. et al. (2024). Understanding User Experience in Large Language Model Interactions. arXiv. https://doi.org/10.48550/arXiv.2401.08329
Search via ReFindit
Wilder, J.W. (1978). New concepts in technical trading systems. Greensboro, NC. https://www.amazon.com/New-Concepts-Technical-Trading-Systems/dp/0894590278
Search via ReFindit
Woerheide, W., & Persson, D. (1992). An Index of Portfolio Diversification. Financial Services Review, 2(2), pp. 73-85. 90003-U https://doi.org/10.1016/1057-0810(92)
Search via ReFindit
Yang, Y., Tang, Y., & Tam, K.Y. (2023). InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuning. arXiv. https://doi.org/10.48550/arXiv.2309.13064
Search via ReFindit
Yang, Y., UY, M.C.S., & Huang, A. (2020). FinBERT: A Pretrained Language Model for Financial Communications. arXiv. http://arxiv.org/abs/2006.08097
Search via ReFindit
Yu, H. et al. (2024). Evaluation of Retrieval-Augmented Generation: A Survey. http://arxiv.org/abs/2405.07437
Search via ReFindit
Yu, W. (2022). Retrieval-augmented generation across heterogeneous knowledge’, in Proceedings of the 2022 conference of the North American chapter of the association for computational linguistics: human language technologies: student research workshop, pp. 52-58. https://doi.org/10.18653/v1/2022.naacl-srw.7
Search via ReFindit
Yu, Y. et al. (2024). Large language model as attributed training data generator: A tale of diversity and bias’, Advances in Neural Information Processing Systems, 36. https://proceedings.neurips.cc/paper_files/paper/2023/hash/ae9500c4f5607caf2eff033c67daa9d7-Abstract-Datasets_and_Benchmarks.html
Search via ReFindit
Zaimovic, A., Omanovic, A., & Arnaut-Berilo, A. (2021). How Many Stocks Are Sufficient for Equity Portfolio Diversification? A Review of the Literature. https://doi.org/10.3390/jrfm14110551
Search via ReFindit
Zamfirescu-Pereira, J.D. et al. (2023). Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts. Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. New York, NY, USA: Association for Computing Machinery (CHI ’23), pp. 1-21. https://doi.org/10.1145/3544548.3581388
Search via ReFindit
Zhao, H. et al. (2024). Revolutionising Finance with LLMs: An Overview of Applications and Insights. arXiv. https://doi.org/10.48550/arXiv.2401.11641
Search via ReFindit
Zhao, P. et al. (2024). Retrieval-Augmented Generation for AI-Generated Content: A Survey. arXiv. https://doi.org/10.48550/arXiv.2402.19473
Search via ReFindit
Zhou, K., Huang, X.M., Yu, D.X., & Cao, J.H. (2025). Integrating the Industrial Chain Information Using Heterogeneous Graph for Portfolio Selection. IEEE Transactions on Consumer Electronics, 71(1), 501-515. https://doi.org/10.1109/TCE.2025.3552780
Search via ReFindit
RSS 1.0