Indonesia is a country that is prone to Dengue Fever, this happens because Indonesia is a country with a tropical climate. More than 50 years after Indonesia contracted the dengue virus, dengue fever cases have not been resolved, currently the cases that occur are greatly increased over time this happens because of factors that cause dengue fever. By considering this serious problem, the authors created a system that can predict the vulnerability level in Bandung and looks for the factors that most influence from all factors of Dengue Fever using the KNN Algorithm and Random Forest. The results of the system show the results of the best model is KNN algorithm with RMSE 29,26, and from the model shows the most influencing factors are population density, growth rate population mobility, rainfall, wind speed. by utilizing the results of the study, the government can adjust actions to each level of sub-district vulnerability and pay more attention to the factors that most influence dengue fever according to the results of the study.

No abstract

No abstract

No abstract

Dengue fever is a dangerous disease caused by the dengue virus. One of the factors causing dengue fever is due to the place where you live in the tropics, so that cases of dengue fever in Indonesia, especially in the Bandung Regency area, will continue to show high numbers. Therefore, information is needed on the spread of this disease by requiring the accuracy and speed of diagnosis as early prevention. In terms of compiling this information, classification techniques can be done using a combination of methods Naïve Bayes, K-Nearest Neighbor(KNN), and Artificial Neural Network(ANN) to build predictions of the classification of dengue fever, and the data used in this Final Project are dataset affected by the spread of dengue fever in Bandung regency in the 2012-2018 period. The hybrid classifier results can improve accuracy with the voting method with an accuracy level of 90% in the classification of dengue fever.