The reality of worldwide population growth and climate change demand that agriculture production can be increased. Traditional study findings which are difficult to extend to all conceivable fields since these are dependent on certain soil types, climatic circumstances, and background management combinations that aren't appropriate or transferable to all farms. There is no way for evaluating the efficacy of endless cropping system interactions (including many management practises) to crop production across the World. We demonstrate that dynamic interactions, that cannot be examined in repetitive trials, which are linked with considerable crop output variability and therefore the possibility for big yield gains, using massive databases and artificial intelligence. Our method can help to speed up agricultural research, discover sustainable methods, and meet future food demands. This is a paper attempted that at crop yield prediction using machine learning techniques with historic crop production data. For this, data has been collected from data.gov.in and data.world.