ENHANCED RANDOM FOREST CLUSTERING ALGORITHM FOR ANALYZING TAMILNADU CROP YIELD PREDICTION USING MACHINE LEARNING METHOD

The computer technology research fields of machine learning and data mining have grown quickly because of developments in data analysis research, the expansion of the database industry, and the ensuing demand from the market for efficient techniques for obtaining valuable knowledge from massive data stores.It is a strong platform that can store and retrieve large amounts of data, but because web development data is diverse and unstructured, searching for information may be a laborious and painful process.As expertise advances, agriculture subdivisions continue to be cultivated in response to community needs.The majority of rural Tamilnadu residents' main source of income.For the majority of the state's rural inhabitants, agriculture continues to be their primary source of income and activity.It is distinguished by wide crop divergence and remnants that are highly dependent on the whims of the southwest monsoon.Half of India's workforce was worked in agriculture, which also contributed 17-18% of the country's 1.4-1.8 per lakh total population during the ten years starting in 2005.This research aims to support agriculturalists in learning about the past crop forecast position using machine learning using effective random forest clustering method.While comparing the existing methods the proposed method gives best result for crop yield prediction in various soils.Compared to other approaches like K-means and K-median, the suggested method ERFCA yields superior results and it helps to improve the productivity of the crops to satisfy food to the human population like as vedic period of India.