Predictive model construction for prediction of soil fertility using decision tree machine learning algorithm

Agriculture sector is recognized as the backbone of Indian economy that plays a crucial role in growth nation’s economy. It imparts on weather and other environmental aspects. Some factors which agriculture reliant are Soil, climate, flooding, fertilizers, temperature, precipitation, crops, insecticides, herb. The soil fertility dependent these hence difficult to predict. However, India facing severe problem increasing crop productivity. Farmers lack essential knowledge nutrient content soil, selection best suited for they also efficient methods predicting well advance so appropriate have been used improve This paper presents different Supervised Machine Learning Algorithms such Decision tree, K-Nearest Neighbor (KNN), Support Vector (SVM) predict based macro-nutrients micro-nutrients status found dataset. algorithms applied training dataset tested with test dataset, implementation done using R Tool. performance analysis evaluation metrics like mean absolute error, cross-validation, accuracy. Result shows tree produced accuracy 99% very less square error (MSE) rate.