Machine learning is a crucial decision-support tool for predicting crop yields, enabling choices about which crops to cultivate and what exactly to do while they are in the developing season. The research on agricultural production prediction has been supported by the application of several machine-learning techniques. Machine learning algorithms can assist farmers in choosing which crop to cultivate in addition to boosting output by considering a variety of factors. The use of yield estimation by farmers can help them minimize crop loss and get the best prices for their produce. In this paper, agricultural yield per acre is predicted using. The paper compares multivariate polynomial regression, support vector machine regression, and random forest using RMSE, MAE, median absolute error, and R-square values.