Running summarizing tools on a new article

Check the paper below, then start its synthesis.


Retracted: Exploring Generative AI Models for Financial Forecasting: A Case Study in Stock Market Predictions

Saurabh Chandra (Bennett University), Reddaiah Kasturi, Spoorthi Golla Vasantha, Vishvanatha Raju, A. Madhuri, Siva Koteswara Rao Katta

IEEE World Conference on Applied Intelligence and Computing (AIC)
License: not stated (all rights reserved)

Abstract: The stock markets are notoriously difficult to accurately predict since they are dynamic, non-linear, and volatile. The use of generative AI for improved event and market movement prediction has recently seen a surge in attention, with a focus on GANs, VAEs, and Transformer-based model architectures. The whole research delves into the possibilities of generative AI models for stock market prediction, using a detailed case study. Our goal is to assess the forecasting capabilities of these time-series models by comparing them to cutting-edge generative methods developed using actual financial data. We demonstrate that generative models provide better prediction accuracy while simultaneously exhibiting intricate relationships and structures that are difficult to convey using conventional methods. Section FINAL discusses the study's limits and consequences, as well as potential future research directions regarding algorithmic trading tactics and financial analytics that make use of generative AI approaches.

Published on 01 Jul. 2025