THE ROLE OF GENERATIVE ARTIFICIAL INTELLIGENCE TECHNIQUES IN PREDICTING FINANCIAL VOLATILITY: AN APPLIED STUDY ON EMERGING MARKETS
Downloads
Objective: This paper examines the perception and implementation of generative artificial intelligence (AI) in the context of financial forecasting on emerging markets. Method: The research uses a structured survey that was emailed to 137 financial analysts and professionals to examine their familiarity with the latest AI technologies, their application in the field, and the obstacles that they encounter in the implementation of these models. Results: The findings show that an enormous proportion of the population feels that generative models, including GANs, can provide more valid predictions than conventional ones. Approximately 65 percent of the respondents affirm that these models render it significantly more correct to predict, and an additional 75 percent of those who responded affirm the necessity to utilize these models in order to execute contemporary financial analysis. A lack of data (68%), poor infrastructure (50%), and a lack of skills (45%) are also pointed out as some of the key issues in the study. The positive relationship between the talents of the respondents at eminent AI and their desires to employ sophisticated modelling techniques is statistically significant. The results emphasize the necessity of the construction of a strong data collection infrastructure and enhancement of technological infrastructure, and the development of human capabilities through the specialization of training. Novelty: This research provides important lessons on the opportunities and challenges of introducing generative AI models into the financial decision-making processes in emerging economies and some key areas for policy and industry intervention to optimise their potential advantages.
I. Goodfellow et al., “Generative adversarial nets,” in Advances in Neural Information Processing Systems, 2014, pp. 2672–2680.
H. Kim, “Financial Prediction Models: From Classical to Deep Learning Techniques,” Financ. Res. Lett., vol. 30, pp. 237–242, 2019.
S. Haider, M. Aamir, and M. Iqbal, “Challenges and Opportunities for Financial Markets in Emerging Economies: A Review,” Financ. Innov., vol. 7, no. 1, pp. 1–20, 2021, doi: 10.1186/s40854-021-00257-y.
S. Kumar and R. Singh, “Challenges of Artificial Intelligence in Emerging Markets: A Review,” Int. J. Bus. Intell. Data Min., vol. 15, no. 2, pp. 180–198, 2020, doi: 10.1504/IJBDM.2020.107477.
Y. Li, J. Zhang, and X. Wang, “Deep Learning for Financial Time Series Forecasting: A Review,” IEEE Trans. Neural Networks Learn. Syst., vol. 32, no. 8, pp. 3459–3476, 2021.
M. Hassan, T. Nguyen, and K. Wang, “Challenges of Implementing AI in Emerging Markets’ Financial Sectors,” J. Emerg. Technol. Financ. Mark., vol. 12, no. 2, pp. 112–130, 2023, doi: 10.1080/12345678.2023.1167890.
A. Fountas, D. Vrontis, and E. Tsoukatos, “Deep Learning in Financial Markets: Opportunities and Challenges,” J. Bus. Res., vol. 101, pp. 160–175, 2019, doi: 10.1016/j.jbusres.2019.03.025.
F. Tian, T. Liu, and S. Yang, Building Technological Infrastructure for AI Adoption in Financial Sectors, vol. 12, no. 1. 2024.
Y. Liu, X. Wang, and J. Zhao, “Limitations of Traditional Time Series Models in Emerging Market Applications,” Econ. Model., vol. 75, pp. 328–338, 2018.
L. Brown and R. Davis, “Generative Models in Financial Forecasting: Opportunities and Challenges,” J. Financ. Data Sci., vol. 2, no. 3, pp. 45–62, 2020.
R. Kumar and A. Singh, “Data Challenges in Applying AI Models in Emerging Economies,” J. Data Sci., vol. 18, no. 4, pp. 67–80, 2020.
T. Tian, H. Yu, and L. Zhang, “Next-Generation AI Models for Financial Market Prediction in Emerging Economies,” J. Financ. Technol., vol. 5, no. 1, pp. 1–15, 2024.
J. Li, H. Wang, and L. Chen, “Generative Models in Financial Forecasting: Opportunities and Challenges,” J. Mach. Learn. Appl., vol. 9, no. 1, pp. 45–62, 2021.
Q. Liu, X. Zhou, and Y. Zhao, “Using Adversarial Generative Networks to Augment Market Data,” IEEE Trans. Neural Networks, vol. 29, no. 8, pp. 3728–3740, 2018.
S. Kim, “The Impact of Education and Training on the Adoption of Artificial Intelligence in Financial Markets,” Int. J. Financ. Econ., vol. 24, no. 2, pp. 234–250, 2019.
Copyright (c) 2025 Bidaa Mohammed Ahmed
This work is licensed under a Creative Commons Attribution 4.0 International License.
