This study presents a comprehensive analysis of machine learning algorithms in predicting Dengue deaths and cases using a dataset containing monthly records of Dengue occurrences per region in the Philippines from 2016 to 2020. The metadata, encompassing temporal and regional attributes, facilitates a nuanced exploration of Dengue dynamics, answering critical questions about peak months, regions with the highest average cases, and overall trends. The application of these predictive models holds significance in public health, offering insights for targeted interventions and resource allocation. The study employs various machine learning algorithms, including Random Forest, Random Tree, Linear Regression, MLP, and SVM Regression, and evaluates their performance using metrics such as correlation coefficients and error measures. Overall, SVM regression performs better and obtained 0.49 correlation coefficient score for the prediction of deaths due to dengue. In dengue disease prediction SVM regression performs better as it achieves highest scores in three evaluation measures. The dataset's richness and the chosen algorithms collectively form a powerful toolkit for understanding and responding to the complex dynamics of Dengue disease, showcasing the practical application of machine learning in addressing public health challenges.