2025, Vol. 10, Issue 9, Part A
Comparative analysis of machine learning-based agricultural price prediction for selected cereal crops in India
Author(s): Ritik Banjare, ML Lakhera, Sweta Ramole and Purnima Sahu
Abstract: Agricultural price prediction is crucial for market stability, farmer income security, and food security planning. In India, staple cereals like paddy and wheat face frequent price fluctuations due to climate variability and production uncertainties, making accurate prediction essential. This study applies machine learning techniques for price prediction using long-term data that includes factors such as Minimum Support Price, area, rainfall, and temperature. Among the tested models, Random Forest proved the most effective, followed by Support Vector Regression and k-Nearest Neighbors, while Decision Tree and traditional regression methods showed weaker accuracy. Random Forest’s ensemble learning capability enabled it to capture complex non-linear relationships and minimize over-fitting. Random Forest stands out as the benchmark method for cereal price prediction in India, providing dependable predicts to guide farmers in crop planning and marketing decisions while supporting a more resilient agricultural economy.
Pages: 56-61 | Views: 259 | Downloads: 4Download Full Article: Click Here
How to cite this article:
Ritik Banjare, ML Lakhera, Sweta Ramole, Purnima Sahu. Comparative analysis of machine learning-based agricultural price prediction for selected cereal crops in India. Int J Stat Appl Math 2025;10(9):56-61.
