The use of technology in the financial industry has experienced sustained growth in recent years. However, in many emerging economies, a significant proportion of the population still does not utilize digital solutions for financial transactions. Promoting financial inclusion through digital environments is essential for driving social and economic development. This study aims to develop machine learning models to predict the adoption of digital payments in Latin America and the Caribbean using statistical data from the World Bank's Global Findex Database for 2021. The performance of the Random Forest, LightGBM, XGBoost, and CatBoost algorithms was compared, with the optimal hyperparameter combination identified through Bayesian optimization. The results show that LightGBM achieved the highest performance in predicting digital payments, with an F1-score of 90.25% and a more stable balance between precision and recall compared to the other models. These findings highlight the value of machine learning models in the financial sector, as they enable a more accurate identification of users adopting digital solutions, facilitating the design of strategies to strengthen financial inclusion in the region.

Despite the growing adoption of artificial intelligence (AI) in healthcare, improving AI frameworks remains essential for effective medical implementation. A major challenge in developing reliable machine learning models is handling imbalanced medical datasets. Although metaheuristic algorithms can improve machine learning performance, their effectiveness on imbalanced medical data has received limited attention. This study evaluates four nature-inspired optimization techniques, bat algorithm (BA), genetic algorithm (GA), improved grey wolf optimization (IGWO), and improved whale optimization (IWO), for enhancing balanced random forest (BRF) classification on imbalanced datasets involving breast tumors, heart failure survival, mammogram microcalcification detection, and diabetes. Based on F1 scores, IGWO achieved the greatest improvements (0.256–0.060), followed by IWO (0.229–0.045), GA (0.214–0.036), and BA (0.203–0.036). Validation results confirmed IGWO’s strong convergence and optimization efficiency, consistently outperforming the other methods. The best performance was achieved by IGWO-BRF in breast cancer diagnosis (F1 = 1.000), while the lowest was observed for BA-BRF in mammogram microcalcification detection (F1 = 0.570). Optimization time depended on both the search strategy and dataset characteristics, with IWO showing the fastest optimization across all datasets. Overall, nature-inspired optimizers significantly improved classification performance on imbalanced medical datasets.