Assessing the Performance of different Machine Learning Techniques to Predict Rainfall in the Northeast Region of Bangladesh

Rainfall prediction is significant and necessary for countries that have based on the agricultural economy like Bangladesh. This paper studies on different machine learning techniques to predict observed Rainfall using meteorological data of Bangladesh Weather Station for the period of January 1956 to December 2015. Different machine learning techniques such as Support Vector Machine (SVM), Naive Bayes (N.B.), Decision Tree (D.T.), and Neural Network (N.N.) were performed three weather stations in the Northeast region: Mymensingh, Sylhet, and Srimangal of Bangladesh. Amazingly, the outcome shows the most available classifier to be Support Vector Machine because of its highest F-measure. Adequate amounts of data have been provided, predicting rainfall using machine learning techniques.