As we all know, in the agricultural industry, farmers and agribusinesses must make countless decisions every day, and the different elements influencing them are complex. The proper yield calculation for the different crops involved in the planning is a critical issue for agricultural planning. Data mining techniques are a critical component of achieving practical and successful solutions to this issue. Agriculture has always been a natural fit for big data. Environmental conditions, soil variability, input amounts, combinations, and commodity pricing have all made it more important for farmers to use data and seek assistance when making vital farming decisions. This research focuses on analyzing agricultural data and determining the best parameters to maximize crop output using machine learning techniques such as Random Forest, Decision Tree and Linear Regression, which can achieve high accuracy. Mining current crop, soil, and climatic data, as well as evaluating new, non-experimental data, improves production and makes agriculture more robust to climate change.