This project focuses on predicting the incidence rate of Dengue fever in a specific region, categorized as either high or low. By utilizing machine learning techniques, such as SVM, XGBoost, and ensemble models like Voting and Stacking classifiers, the system processes various input parameters such as temperature, humidity, rainfall, reported cases, population density, season, vector control, urbanization level, and healthcare access. These features play a vital role in determining the severity of dengue fever incidence. To further enhance transparency, the model employs LIME for explainable AI, allowing users to understand how specific features impact predictions. The project is developed with a Flask backend and MySQL database, with a user-friendly frontend built using HTML, CSS, and JavaScript. By automating the prediction of dengue fever incidence, this system aims to assist healthcare professionals and policymakers in resource allocation and preventive measures.

Keywords: Dengue Fever,  Incidence Rate Prediction , Machine Learning , SVM , XGBoost, Ensemble Models , Stacking Classifier , Voting Classifier , Explainable AI , LIME , Flask, MySQL