This research investigates the utilization of machine learning methodologies, particularly Random Forest and Decision Tree algorithms, to categorize Indian Ocean Dipole (IOD) occurrences by employing Sea Surface Temperature (SST), Mean Sea Level Pressure (MSLP), and total precipitation datasets derived from the maritime region adjacent to West Sumatra. The study leverages data amassed from 2020 to 2024, concentrating on diverse climatic scenarios linked to IOD. The efficacy of both algorithms is assessed using evaluative criteria such as accuracy, precision, and recall. The findings reveal that the Random Forest algorithm surpasses the Decision Tree algorithm, attaining an accuracy rate exceeding 85%, with SST recognized as the predominant predictor. These results underscore the promise of machine learning techniques in advancing the comprehension of IOD and its ramifications on regional meteorological trends, thereby facilitating enhanced climate forecasting models and guiding decision-making frameworks for climate adaptation.