In India, agriculture plays a crucial role in boosting the economy. However, traditional methods of cultivation often result in poor crop yields due to bad weather conditions, leading to financial losses for farmers. Machine learning techniques have shown promise in improving crop prediction accuracy, surpassing traditional methods. To this end, we collected a crop dataset with parameters such as temperature, humidity, rainfall, and pH, and trained various machine learning algorithms including KNN, and DTC classifiers. Our experimental results indicate that the Voting ensemble classifier achieved the highest accuracy of 87.21% among all classifiers, making it a reliable option for crop prediction. We have proposed one ensemble learning model (KNN+DTC), its accuracy is 92%, and precision, and recall is 90%. In this manuscript, we have applied the ensemble approach which performs well in comparison to individual classifiers’ performance. There are two approaches adopted one before ensemble learning and the second one after ensemble learning. The obtained result shows that after ensemble learning performance is good.