India is an agriculture-producing country. Weather, climate changes, rainfall patterns, usage of fertilizers, etc. are the main hazards that damage crops. Hence, crop yield prediction is essential for choosing the right soil for the right crop to improve crop production. Machine Learning (ML) is a rapidly growing technology in all trending areas and performs classification and prediction analysis. In this paper, an endeavor has been made to improve crop production using ML algorithms. One hundred crop yield data sets are considered, which consist of six influence input parameters and one significant output parameter, Multiple Linear Regression (MLR), Decision Tree Regressor, Support Vector Regression (SVR), Random Forest (RF) in Linear regression, Back Propagation Neural Network (BPNN), and Radia Basis Function Neural Network (RBFNN) were developed to predict the yield of the crop. Among all models, the yielded outcomes show that the RF model gives a high accuracy of 99.74% and less RMSE of 0.2179.