Shahzad Anwar
The article presents a novel artificial intelligence based computational cloud-based financial market simulator and prediction model. The proposed system incorporates the state-of-the-art generative models, including the Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), diffusions alongside combinations of hybrid time-series forecasting networks, including Prophet-LSTM or Transformer-based architectures. The framework operates at scale on the distributed cloud platforms (aws, Azure, GCP) that help to train and serve in parallel and provide training and real-time inference. According to the provided experimental analysis of the use of the S and P 500 and cryptocurrency as models reveals a higher accuracy of 94.7% in prediction, a lower mean error of 15.3% and a reduced time of 3.2 longer to train when trained on the basis of parallelization in a cloud-based environment. The system exhibits high scenarios bearing capabilities which are 10,000 synthetics produced in a second at statistical accuracy up to the past tendencies. The research contributes to the creation of financial technology through synergistic integration of generative AI, cloud computing, and quantitative finance methods.
Shahzad Anwar “Generative AI-Driven Financial Market Simulation and Forecasting Using Cloud-Based Vol. 12 Issue 11 PP. 197-206 November 2025. https://doi.org/10.5281/zenodo.17661001.
[1] J. Li, Y. Liu, W. Liu, S. Fang, L. Wang, C. Xu, and J. Bian, “MarS: A financial market simulation engine powered by generative foundation model,” arXiv preprint arXiv:2409.07486, 2024. DOI: 10.48550/arXiv.2409.07486.
[2] D. Patel, G. Raut, S. N. Cheetirala, G. N. Nadkarni, R. Freeman, B. S. Glicksberg, E. Klang, and P. Timsina, “Cloud platforms for developing generative AI solutions,” arXiv preprint arXiv:2412.06044, 2024. DOI: 10.48550/arXiv.2412.06044.
[3] M. Chen, S. Mei, J. Fan, and M. Wang, “Opportunities and challenges of diffusion models for generative AI,” National Science Review, vol. 11, no. 12, p. nwae348, 2024. DOI: 10.1093/nsr/nwae348.
[4] S. Kwon and Y. Lee, “Can GANs learn the stylized facts of financial time series?” in Proc. 5th ACM Int. Conf. AI Finance (ICAIF ’24), 2024, pp. 1–8. DOI: 10.1145/3677052.3698661.
[5] Z. Wang and C. Ventre, “A financial time series denoiser based on diffusion models,” in Proc. 5th ACM Int. Conf. AI Finance (ICAIF ’24), 2024, pp. 1–9. DOI: 10.1145/3677052.3698649.
[6] S. S. Dubey, V. Astvansh, and P. K. Kopalle, “Generative AI solutions to empower financial firms,” Journal of Public Policy & Marketing, vol. 44, no. 3, pp. 411–435, 2025. DOI: 10.1177/07439156241311300.
[7] K. M. Antony, “An empirical analysis of the impact of cloud computing and distributed systems on corporate finance decision-making, risk management, and financial performance in a digitally transformed economy,” International Journal of Finance, vol. 38, no. 2, pp. 1–25, 2025. DOI: 10.34218/IJFIN.38.2.001.
[8] S. K. Mogali, “Transforming digital banking with AI-enhanced cloud infrastructure: A strategic perspective on risk management,” Economic Sciences, vol. 21, no. 1, pp. 396–407, 2025. DOI: 10.69889/j7sgrw39.
[9] H. Takahashi and T. Mizuno, “Generation of synthetic financial time series by diffusion models,” Quantitative Finance, vol. 25, no. 3, pp. 1–20, 2025. DOI: 10.1080/14697688.2025.2528697.
[10] C. Sai, V. Kumar, and P. Sharma, “Generative AI for finance: Applications, case studies and challenges,” Expert Systems, vol. 42, no. 2, p. e13760, 2025. DOI: 10.1111/exsy.70018
