Abstract
Dengue fever is one of the fastest-growing mosquito-borne infectious diseases worldwide, particularly affecting tropical and subtropical regions. Early prediction of dengue outbreaks is essential for effective public health planning and disease prevention. This study proposes a machine learning–based framework to predict dengue outbreaks using climate and environmental variables such as temperature, rainfall, humidity, and wind speed. Historical dengue case data and meteorological information are integrated to train predictive models including Random Forest, Support Vector Machine, and Gradient Boosting algorithms. The dataset is preprocessed using normalization and feature selection to identify key climatic risk factors influencing dengue transmission. Experimental results demonstrate that machine learning models can accurately forecast dengue outbreaks several weeks in advance, achieving high prediction accuracy and improved reliability compared to traditional statistical methods. Th