Leveraging artificial intelligence models for financial forecasting

Download This Article

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstact

This study investigates the predictive validity of generative artificial intelligence (AI) in financial forecasting. Specifically, it evaluates the zero-shot forecasting capabilities of GPT-4o and Claude Sonnet 3.5 by comparing their predicted stock prices against actual closing prices from a cross-industry portfolio as of February 3, 2025. Utilizing standardized statistical measures such as mean absolute error (MAE), root mean squared error (RMSE), mean absolute percentage error (MAPE), correlation coefficients, and R², the study finds that Claude Sonnet 3.5 consistently outperforms GPT-4o in predictive accuracy and correlation. The research also examines directional bias and sector-specific performance.

Keywords: AI Forecasting, GPT-4o, Claude Sonnet 3.5, Financial Modeling, Stock Prediction, Machine Learning

JEL Classification: G17, C53, C45, G11

Received: 31.03.2025
Accepted: 05.05.2025

How to cite: Akpan, M. (2025). Leveraging artificial intelligence models for financial forecasting. In A. M. Gallo, U. Comite, & A. Kostyuk (Eds.), Corporate governance: International outlook (pp. 17–23). Virtus Interpress. https://doi.org/10.22495/cgiop3