This paper demonstrates on how the machine learning models can be used in predicting the crops that can be grown on the suitable environment based on the given data of the farms. The models which we used, can help to forecast the outputs based on the certain parameters: soil pH, potassium, nitrogen, phosphorous, rainfall, and humidity. The Historical data of soil types, the percentage of the nutrients present in the soil and the corresponding minerals information are gathered and preprocessed to develop a robust dataset. We collect the input data from the user by measuring through the IOT sensors and compare it with the test data through certain machine learning models. The linear regression model is developed on these features to accurately predict the outputs. The results produced by our system will help the farmers in estimating the price for cultivation of the specified crops. This approach offers a cost-effective solution for the harvesting of the crops and also produces more precisive results which can be useful for precision agronomy. This proposed model integrates all the ML applications for providing assistance in the prediction of the crops. The incorporation of this model into the agricultural domain promises considerable improvements in crop cultivation, crop price estimation and soil mineral assessment. This research will help the farmers in choosing the crops which are subtle for current farming conditions.