Dengue has been reported as a major cause of morbidity and mortality for the last 40 years worldwide including Malaysia. This work develops and implements visualization and predictive modelling for dengue in Malaysia. The incidences are visualized using Geographical Information System (GIS) which provides information on coordinates (latitude and longitude) based on the occurrence of incidences registered with the Disease Control Division of the Ministry of Health, Malaysia. Clustering is performed on this data using centroid and distribution models that are representatives of K-means and the Expectation Maximization (EM) algorithms, respectively. The results are validated for Petaling district of Selangor and are shown to possess good performance in predicting the dengue incidences. The proposed method is able to localize the incidences which can further be utilized for vector disease control processes. © 2016 IEEE.