A major challenge in crop yield prediction is the factors affecting the selection of crop like environment, crop types and soil type. Different machine learning approaches have been used for the prediction of crop yield. This study aims to determine the most accurate and efficient method for predicting crop yields, which could aid farmers in making informed decisions about crop management and improve food security. This research paper explores the effectiveness of machine learning approaches for predicting crop yields. The study used logistic regression, decision tree classifier, random forest classifier, XGBoost and K-Nearest Neighbours algorithms to predict crop yields using a range of variables like N, P, K, temperature, humidity, Ph and rainfall. The results indicate that machine learning approaches have the potential to improve crop yield prediction accuracy and could be an effective tool for crop management in the future. The study shows that random forest algorithm is giving a high accuracy of 98.03 % compared to decision tree, XGBoost and KNN algorithms