This research project explores the optimization of the family selection process for participation in Uruguay's Crece Contigo Family Support Program (PAF) through machine learning. An anonymized database of 15,436 previous referral cases was analyzed, focusing on pregnant women and children under four years of age. The main objective was to develop a predictive algorithm capable of determining whether a family meets the conditions for acceptance into the program. The implementation of this model seeks to streamline the evaluation process and allow for more efficient resource allocation, allocating more team time to direct support. The study included an exhaustive data analysis and the implementation of various machine learning models, including Neural Networks (NN), XGBoost (XGB), LSTM, and ensemble models. Techniques to address class imbalance, such as SMOTE and RUS, were applied, as well as decision threshold optimization to improve prediction accuracy and balance. The results demonstrate the potential of these techniques for efficient classification of families requiring assistance.

This study presents a comprehensive methodology for modeling and forecasting the historical time series of active fire spots detected by the AQUA\_M-T satellite in the Amazon, Brazil. The approach employs a mixed Recurrent Neural Network (RNN) model, combining Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures to predict the monthly accumulations of daily detected active fire spots. Data analysis revealed a consistent seasonality over time, with annual maximum and minimum values tending to repeat at the same periods each year. The primary objective is to verify whether the forecasts capture this inherent seasonality through machine learning techniques. The methodology involved careful data preparation, model configuration, and training using cross-validation with two seeds, ensuring that the data generalizes well to both the test and validation sets for both seeds. The results indicate that the combined LSTM and GRU model delivers excellent forecasting performance, demonstrating its effectiveness in capturing complex temporal patterns and modeling the observed time series. This research significantly contributes to the application of deep learning techniques in environmental monitoring, specifically in forecasting active fire spots. The proposed approach highlights the potential for adaptation to other time series forecasting challenges, opening new opportunities for research and development in machine learning and prediction of natural phenomena. Keywords: Time Series Forecasting; Recurrent Neural Networks; Deep Learning.

Google in February did something it's never done before: It told the world just how big its Google Cloud business really is. The search giant said its six-year-old cloud platform and its popular cloud-based collaboration portfolio, G-Suite, is now a $1 billion per quarter business. To sustain that growth, Google is leaning more heavily on its capabilities in artificial intelligence (AI), and machine learning. To pull in bigger deals, Google needs solution providers to help them reach businesses where AI and machine learning will matter most. Agosto, a Minneapolis-based Google partner, is seeing an increase in the number of Fortune 500 companies that are looking at Google as a feature-by-feature competitor of AWS and Microsoft.