Rice production plays a vital role in ensuring food security and promoting agricultural development in Nigeria. This study compared the performance of the K-Means and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithms in classifying rice yields across the 36 states of Nigeria and the Federal Capital Territory (FCT). Rice yield data for 2023 were obtained from the National Agricultural Extension and Research Liaison Services (NAERLS), Ahmadu Bello University, Zaria. K-Means partitioned the data into six clusters with an overall average silhouette width of 0.39, whereas DBSCAN identified three clusters and six noise points. Comparative analysis showed that DBSCAN achieved better clustering performance, with 31 allocated states compared with 29 for K-Means. The clustering patterns revealed regional similarities in rice yields, providing valuable insights for targeted agricultural planning and resource allocation. The findings demonstrate that DBSCAN is more effective than K-Means for clustering heterogeneous rice yield data, offering a reliable framework for evidence based agricultural planning and policy formulation in Nigeria.