• Sasikumar Peyyala
• Eeda Damodara Rao

This study focuses on analyzing the success of integrating the conventional machine learning algorithms with semantic intelligence generated by large language models (LLMs) like the ChatGPT-4o in generating NASDAQ-100 stock prediction portfolio strategies between the years 2020–2025. Through testing new combinations of ML- and LLMetrics of semantic, three prediction frameworks are evaluated the basic, technical and entropy-based prediction frameworks. Regarding the best blending processes, the empirical findings indicate that the methods differ greatly. In particular, the technical methodology produces the most desirable results when it comes to using only ML projections, and with monthly rebalancing, it has cumulative returns of nearly 1978%. Conversely, the foundational technique will show its best when it is largely founded on the semantic insights that are acquired by using LLM. The better solution to enhance the Entropy technique can exist by adding both semantic and ML prediction signals. It is implied that LLMs can possibly enhance predictive performance because they can offer an explanatory model about complex market dynamics. These results all have an implication in portfolio management, further research in the domain of financial modeling, and the importance of mapping the semantic-algorithmic fusion to predictive data features and investing horizons.

artificial intelligence, trading, fuzzy logic, technical, fundamental.

"RISK-AWARE STOCK PRICE PREDICTION MODEL USING HYBRID AI", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 1, page no.f430-f440, January-2026, Available :http://www.jetir.org/papers/JETIR2601563.pdf

"RISK-AWARE STOCK PRICE PREDICTION MODEL USING HYBRID AI", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 1, page no. ppf430-f440, January-2026, Available at : http://www.jetir.org/papers/JETIR2601563.pdf