Abstract

Ensuring agricultural profitability is a vital issue in developing countries like India, where over a third of the population earns their income directly or indirectly through agriculture. Estimating and evaluating crop yields is done globally to achieve high yields and appropriate pricing. However, there is no accurate procedure in place to provide farmers with insights on which crops should be grown. This project aims to predict crop prices by analysing historical data, such as precipitation, temperature, market prices, land area, and crop yield, using supervised machine learning models. We have focused on crops from the Rabi and Kharif seasons and applied models like Decision Trees, Random Forest, and Support Vector Regression to develop a robust system for predicting crop prices, providing farmers with data-driven insights for decision-making.