Integrating recursive feature selection with automated machine learning framework for global wheat price prediction

Abstract

Wheat price forecasting is challenging due to the interplay between economic trends, environmental variability and unpredictable market conditions, as well as the scarcity of reliable data. This research presents an innovative method for predicting global wheat prices by combining Recursive Feature Elimination with Cross Validation (RFECV) and Bayesian Ridge Regression in an Automated Machine Learning (AutoML) framework. The inclusion of key input variables - Lag 1, Lag 2 and an outlier indicator, marks a significant improvement in capturing regular and extreme market events which have a strong impact on prices. A comprehensive evaluation was conducted using 32 years of monthly wheat price data (1990–2022) from the Federal Reserve Economic Database, comparing 35 machine learning models. . Based on test set performance, top five performing models i.e. Bayesian Ridge, Linear Regression, Least Angle Regression (Lars), Least Angle Regression with Cross-Validation (LarsCV) and Least Absolute Shrinkage and Selection Operator Least Angle Regression with Cross-Validation (Lasso Lars CV), were selected and further assessed across four train-test splits (80:20, 75:25, 70:30 and 65:35). The 80:20 split provided the most stable results, with Bayesian Ridge achieving the lowest RMSE of 12.26, outperforming the other models by 1.39% to 2.61% across all splits. These findings highlight the model’s generalizability and potential application in policy formulation, market regulation and strategic planning for global wheat trade.