Abstract

Abstract: India is an agriculture based country. Farming and farm related business are mainly focused for earning bymajor population. Farmer has to make decisions manually every year for various factors such as crop to be cultivated,choosing a fertilizer quantity as per soil properties. The decisions made are not accurate as it does not consider soilproperties. To overcome this problem, researchers have analysed the agricultural data for various parameters. In thisdissertation work, we are going to use agricultural data which will be region specific. PAM, CLARA, modified DBSCANdata mining culturing techniques are used in literature. We are going to use machine learning techniques namelymultiple linear regression, SVM, KNN and ANN for crop yield prediction. Predicting those results on parameters of soilproperty like NPK values, temperature and rainfall. From this analysis, farmer can get accuracy and clarity to getdecision for crop to be cultivated to get better product yield while considering environmental factors, weather conditions,soil types and season.Keywords- Machine learning, Data mining, Agriculture