Can ChatGPT Predict Stock Market Price Movements?

Karamveer Singh; Karamveer Singh

Karamveer Singh Maharaja Surajmal Institute of Technology C-4 Janak Puri New Delhi-110058
Karamveer Singh Maharaja Surajmal Institute of Technology C-4 Janak Puri New Delhi-110058

Abstract

The combination of text analytics and machine learning technologies in various applications has emerged recently. Generative content creation platforms use machine learning, which is not only restricted to text but also considers other types of data, i.e., graphs, images, and knowledge bases. The Generative platforms such as ChatGPT and other tools focus on multi-modal knowledge extraction, a challenging area in Machine Learning. Advanced generative models generate large amounts of consolidated information with different characteristics to address data accessibility issues. ChatGPT and other generative mechanisms are extensively applied in various domains, the financial market being significant. Using state-of-the-art linguistic models, we analyze the potential of ChatGPT to predict stock price growth using Indian news headlines, offering a promising outlook for the financial market. The main challenge is determining whether a model originally developed for commonly understood language can predict the success of banks in a complex and dynamic market. The study, a pioneering effort, provides valuable insights into the benefits and implications of ChatGPT in the economy, shedding light on its market research, risk assessment and sentiment analysis capabilities. It is one of the first attempts to addition to its use in text explore the use of ChatGPT in the Indian economy. In analytics, ChatGPT holds promise as a valuable asset for financial professionals, providing flexibility and sensitivity analytics capabilities in navigating the challenges of a volatile industry. As the financial sector evolves, continued research and development to leverage the full potential of language models such as ChatGPT will help enhance market research and decision-making processes. Integrating AI-powered solutions in finance has exciting possibilities for real-time insights and adaptive analysis.

References

[1] Hansen, Anne Lundgaard., Kazinnik, Sophia (2023). Can Chatgpt decipher Fedspeak? Available at SSRN, SSRN Electronic Journal. 4399406.. [2] Yang, Kai-Cheng., Menczer, Filippo (2023). Large language models can rate news outlet credibility, 2023. https://arxiv.org/abs/2304.00228 [3] Lopez-Lira, Alejandro., Tang, Yuehua (2024). Can chatgpt forecast stock price movements? return predictability and large language models, https:// www.anderson.ucla.edu/sites/default/files/document/ 2024-04/4.19.24%20Alejandro%20L opez%20Lira%2 0ChatGPT_V3.pdf [4] Noy, Shakked., Zhang, Whitney. Experimental evidence on the productivity effects of generative artificial intelligence. Available at SSRN 4375283, 2023. [5] Xie, Qianqian., Han, Weiguang., Lai, Yanzhao., Peng, Min., Huang, Jimin. The Wall Street Neophyte: A zeroshot analysis of ChatGPT over multimodal stock movement prediction challenges, 2023. Papers 2304.05351, arXiv.org, revised Apr 2023 [6] Jegadeesh, Narasimhan., Wu, Di (2013). Word power: A new approach for content analysis. Journal of Financial Economics, 110 (3)712â€“729, 2013. [7] David E. Rapach, Jack K. Strauss, and GuoFU ZHOU. International stock return predictability: What is the role of the United States? The Journal of Finance, 68 (4)16331662, 2013. [8] Hoberg, Gerard., Phillips, Gordon. (2016). Textb based network industries and endogenous product differentiation. Journal of Political Economy, 124 (5)1423â€“1465, 2016. [9] Baker, Scott R., Bloom, Nicholas., Davis, Steven J..(2016) Measuring Economic Policy Uncertainty. The Quarterly Journal of Economics, 131 (4):1593â€“1636, 07 [10] Hutto, Clayton., Gilbert, Eric (2014). Vader: A parsimonious rule-based model for sentiment analysis of social media text. In: Proceedings of the international AAAI conference on web and social media, volume 8, p.216225. [11] Cowen, Tyler., Tabarrok, Alexander T. (2023) How to learn and teach economics with large language models, including gpt. Including GPT (March 17, 2023), 2023. [12] Anton Korinek. (2023). Language models and cognitive automation for economic research. Working Paper 30957, National Bureau of Economic Research, February 2023. [13] Hyungjin Ko and Jaewook Lee. (2024) Can ChatGPT improve investment decisions? From a portfolio management perspective, Finance Research Letters, Volume 64. June 2024, 105433. [14] Chang Che, Zengyi Huang, Chen Li, Haotian Zheng, and Xinyu Tian. (2024) Integrating Generative AI into Financial Market Prediction for Improved Decision Making. arXiv. https://arxiv.org/abs/2404.03523 [15] Subba Rao Polamuri, Kudipudi Srinivas, A. Krishna Mohan (2022). Multi-Model Generative Adversarial Network Hybrid Prediction Algorithm (MMGAN-HPA) for stock market price prediction, Journal of King Saud University Computer and Information Sciences, 34 (9) 7433-7444. [16] Kuo, C. -H. Chen, C. -T.. Lin, S. -J., Huang, S. -H. (2021). Improving Generalization in Reinforcement Learningâ€“Based Trading by Using a Generative Adversarial Market Model, IEEE Access, vol. 9, p. 50738-50754, 2021, doi: 10.1109/ACCESS. 2021.3068269. [17] Bai, X., Zhuang, S., Xie, H., Guo, L. (2024). Leveraging Generative Artificial Intelligence for Financial Market Trading Data Management and Prediction. Preprints 2024, 2024070084. https://doi.org/10.20944/preprints202407 .0084.v1 [18] Staffini, Alessio (2022). Stock Price Forecasting by a Deep Convolutional Generative Adversarial Network, Frontiers in Artificial Intelligence, VOLUME 5, Article no. 1. p. 1-16 [19] Wade, Toby J. (2024) Transformers and tradition: using Generative AI and Deep Learning for financial markets prediction. PhD thesis, London School of Economics and Political Science.[20] Coletta, Andrea and Prata, Matteo and Conti, Michele and Mercanti, Emanuele and Bartolini, Novella and Moulin, Aymeric and Vyetrenko, Svitlana and Balch, Tucker (2022) Towards realistic market simulations: a generative adversarial networks approach, (46), 9. In: ICAIF '21. ACM [21] Prata, M., Masi, G., Berti, L. et al. Lob-based deep learning models for stock price trend prediction: a benchmark study. Artificial Intelligence Review 57, 116 (2024). https://doi.org/10.1007/s10462-024-10715-4 [22] Chen, B., Wu, Z., Zhao, R. (2023). From fiction to fact: the growing role of generative AI in business and finance. Journal of Chinese Economic and Business Studies, 21(4), 471â€“496. https://doi.org/10.1080/ 14765284.2023.2245279