The field of agriculture contributes to the economic growth of several countries in the world, especially in developing nations, wherein the bulk of the population relies on agriculture for their survival. The prediction of the yield of crops helps in increasing agricultural efficiency, ensuring food security, and aiding the decisions of farmers as well as policy makers. The machine learning techniques of predicting yields prove to be quite lengthy, costly, and inaccurate due to uncertain climatic situations. This research paper is related to an investigation into crop yield prediction through the use of different machine learning algorithms like Linear Regression, Random Forest, Decision Tree, SVM, and ANN. The current system uses environmental and agricultural factors like rainfall, temperature, soil quality, humidity, and fertilizers for crop yield prediction with high accuracy. A comparative analysis of different machine learning systems is carried out based on performance measures like MAE, RMSE, and accuracy. As compared to other traditional statistical approaches Random Forest provide higher prediction accuracy. This paper elaborates how machine learning can contribute toward precision agriculture and sustainable framing.