Abstract:
In the present article, an attempt has been made to derive optimal data-driven machine learning methods for forecasting an average rainy season (June to September, 1901-2018) rainfall of the state of India. This comparative analysis is based on three aspects: pre-processing techniques input modeling and modeling methods. Comparisons among the four linear regression analysis, random
forest method, Decision Tree and Navie Bayes method have been considered to find out a best prediction technique. In this study it has been observed that the maximum rain fall 385.3mm occurred in year 1961and minimum197.2mm rain fall occurred in year 1974.It has been found that maximum accuracy for Random forest regression 91% and mean absolute error was 2.3%, for Navie bayes accuracy was 89.64% and mean absolute error was 3.2%,for Linear regression accuracy was 87.28% and mean absolute error was 3.8%.from the present study it has been observed that Random forests is a viable model to be used in the field of rainfall prediction.

Objective:
Objective Rainfall is very important because heavy and irregular rainfall can have many impacts like destruction of crops and farms, damage of property so a better forecasting model is essential for an early warning that can minimize risks to life and property and also managing the agricultural farms in better way.