Kisan Dhan - Crop Price Prediction Using Random Forest

Abstract

Accurate prediction of agricultural commodity prices holds an important role for ensuring food security, profitability for farmers in farming, and making well-informed decisions for both farmers and industry stakeholders. Most of the prediction is made for farmers in the proposed system. The proposed system aims to find the relationship between weather conditions and agricultural prices by utilizing a comprehensive dataset spanning past years, including historical price data, modal, maximum and minimum prices, productivity, production and key meteorological things affecting like rainfall and temperature. The system also uses machine learning algorithms to classify the effects of climate factors, on price variations in combination with data collection. In addition to showing superior prediction capacity of the Random Forests than Decision Trees, this project is very good and major in terms of agriculture prices. These findings offer a good prediction for farmers in the agricultural industry to make secured decisions and face the challenges of price volatility. In a world where the stability of food production and economic sustainability depends on price predictability, this project contributes a practical and powerful tool for enhancing the prediction of the agricultural sector.