AGRICULTURAL COMMODITY PRICE FORECASTING WITH COMPETITIVE ENSEMBLE REGRESSION TECHNIQUE

R. Ragunath, R. Rathipriya

Abstract

This research study focuses on introducing a novel ensemble learning-based strategy using
regression models to enhance the accuracy of forecasting Agricultural Commodity Price (ACP)
trends. The main objective is to give farmers and traders better accurate pricing forecasts. The
study uses data from India's rainfall data and the Wholesale Pricing Index (WPI) for essential
commodities to test a variety of regression models, including ensemble regression models. The
empirical results highlight the competitive ensemble approach's greater accuracy in capturing
directional shifts in agricultural commodity pricing when compared to conventional regression
models. As a result, this strategy has a lot of potential for assisting decision-making in the food
and financial industries.