This article represents the result of extensive research and application of mathematical regression models based on machine learning. These models have been developed with the purpose of predicting numerical values from historical data collected from the National Anti-Corruption Index (INAC), until their last validity. This index, conceived as a compendium of measurements generated and evaluated by various public entities, is an integral indicator that reflects national efforts in the fight against corruption. INAC’s measurement focuses on evaluating anti-corruption policies and tools in order to analyze institutional capacities in this area. Open access to this information facilitates analysis and evaluation by researchers and the general public. The primary objective of this study is to identify the most effective regression models for predicting INAC values and, therefore, to generate transparency indicators that contribute to the effective management of public resources. This analytical approach is based on the need to develop robust and reliable tools to support informed decision-making in the context of anti-corruption and the promotion of institutional integrity.