Comparison of machine learning models for oilseed price prediction

Abstract

Sunflowers are vital for agricultural economic growth, food security, and improving pollination for other crops. However, accurately forecasting sunflower prices is challenging due to factors such as fluctuating supply and weather conditions. This study evaluates the performance of various machine learning models viz., Artificial Neural Networks (ANN), Support Vector Regression (SVR), K-Nearest Neighbors (KNN), and Random Forest (RF) for predicting sunflower prices. The analysis uses monthly wholesale price data from January 2010 to June 2024 for the Bellary and Gadag markets in Karnataka, India, obtained from AGMARKNET. The findings reveal that the RF model outperforms the other models, demonstrating its superior effectiveness in predicting sunflower prices compared to the other machine learning approaches.