Crop Yield and Price Prediction Using Multifactorial Analysis
Prof. Sulochana Sonkamble1, Tanmay Chaudhari2, Umesh Sake3, Vinanti Shinde4, Srushti Ghise5, Nikita Girase6
1Sulochana Sonkamble, Computer Department, JSPM NTC
2Tanmay Chaudharai, Computer Department, JSPM NTC
3Umesh Sake, Computer Department, JSPM NTC
4Vinanti Shinde, Computer Department, JSPM NTC
5Srushti Ghise, Computer Department, JSPM NTC
6Nikita Girase, Computer Department, JSPM NTC
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Agriculture plays a critical role in sustaining economies and feeding populations, especially in countries like India, where a significant portion of the workforce depends on it. However, crop yield is highly influenced by numerous environmental and soil-related factors, making prediction and decision-making challenging for farmers. This study presents a data-driven crop yield prediction and market analysis system that leverages machine learning and real-world agricultural data to provide accurate yield forecasts. Using a cleaned dataset comprising key features such as temperature, rainfall, soil nutrients (N, P, K), pH, and crop type, a regression-based predictive model was developed to estimate the yield in tons per hectare. Additionally, an economic perspective was integrated through the analysis of market price trends from regional data, aiding in crop selection based on both productivity and profitability. The proposed system, supported by an interactive interface, empowers stakeholders to make informed agricultural decisions, thereby enhancing productivity and economic returns. The experimental results demonstrate the effectiveness and potential of the model to support smart agriculture initiatives.
Key Words: Machine Learning Crop Yield Prediction, Machine Learning, XGBoost Regressor, Random Forest, Gradient Boosting, Precision Agriculture, Soil Analysis, Agricultural Forecasting, Market Price Analysis, Sustainable Farming
