MODELING FINANCIAL WITH INTELLIGENCE ARTIFICIAL: ANALYSIS OF PLATFORMS, FRAMEWORKS AND APPLICATIONS IN MERGERS VALUATION

This study explores the development of Artificial Intelligence (AI) solutions applied to financial modeling, with a focus on the evaluation of business mergers. The research contextualizes the growing relevance of AI technologies for analyzing financial scenarios, highlighting the challenges in choosing appropriate platforms and frameworks. The problem addresses the difficulty of identifying best practices for using these tools in complex assessments. The general objective was to identify and analyze the ideal practices for developing AI solutions in financial valuation. The methodology adopted the Giftedean neoperspectivist paradigm, integrating the Theory of Statistical Learning, the Theory of Complex Adaptive Systems and the Theory of Distributed Computing, using the hypothetical-deductive method to test hypotheses. Computational simulations in Google Colab and machine learning techniques were used. of machine. You findings indicate what the combination of platforms online and frameworks such as TensorFlow and PyTorch enhance the accuracy of the models, although there are gaps related to accessibility and automation of deployment. The theoretical contributions include an integrated approach to financial data analysis, while the methodological and empirical contributions cover a practical guide for application in mergers. The research adds value by providing practical insights for technology selection, contributing to more accurate decision-making in complex business processes.