This study investigates the relationship between climatic factors and dengue fever incidence in Bangladesh using machine learning (ML) clustering techniques, specifically K-means, DBSCAN, and Affinity Propagation (AP). The dataset, spanning 2008–2018, includes variables such as minimum and maximum temperature, rainfall, humidity, and reported dengue cases. Quantitative analysis reveals that rainfall exhibits a moderate positive correlation (0.37) with dengue cases, while humidity shows a weaker correlation (0.28). The clustering methods identified high-risk periods and regions, particularly during the monsoon season. AP achieved the best performance, with a mean dengue incidence of 2429.67 cases in its primary cluster, surpassing DBSCAN (1706 cases) and K-means (431.23 cases). Evaluation metrics, including the Silhouette Score (0.49), Calinski-Harabasz Index (149.74), and Davies-Bouldin Score (0.73), highlight AP’s superior cluster cohesion and separation. The findings provide actionable insights for optimizing resource allocation and planning public health interventions during peak transmission periods. This framework demonstrates how ML can enhance predictive accuracy and support targeted dengue control strategies under varying climatic conditions.