Analyzing Supervised Learning Algorithms for Crop Prediction and Soil Quality

India is one of the most developing countries wherein agriculture performs a significant position within the nation's economy subsequently growing agricultural productiveness. Crop yields have been declining day by day as a result of their reliance on highly unpredictable causes like monsoon, soil, etc. Yield of the crop is affected by soil type because crops absorb major nutrients through the soil. Each sort of soil can have a number of properties and each crop better grows in a specific type of soils. Machine learning approaches can aid in better horticulture decisions for crop selection. Crop yield prediction is predicting the crop's production based on historical data that includes elements such as pH value, temperature, humidity, rainfall, and crop name. It directs us to a research field of best-predicted crop that would be grown in the field under the given weather circumstances. Machine learning techniques were used to undertake a comparative analysis of soil parameters to forecast crop production in the suggested work. The Naïve Bayes (NB) method, Logistic Regression (LR) algorithm, and Random Forest (RF) algorithm are used to forecast agricultural yield.