An explainable AI-enabled granular ensemble machine learning framework to demystify fertilizer price movements

Abstract

This paper proposes a novel explainable artificial intelligence (AI) driven ensemble machine learning (ML) framework for predicting fertilizer price movements and assessing the contributions of the technical and macroeconomic indicators. We integrate the Boruta algorithm, Maximal Overlap Discrete Wavelet Transformation (MODWT), Random Forest (RF), and explainable AI. The predictive analytics exercise utilises the residual of the previous stage as an additional indicator for arriving at the subsequent stage forecasts. We observe a significant influence of the residual in providing forecasts for time series with higher frequencies. The explainable AI is used at the global and local levels to explain the impacts of the indicators on fertilizer price movements. We have used monthly urea and diammonium phosphate (DAP) prices for nearly the last 30 years for predictive analytics. The explainable AI identifies the more significant impacts of the technical indicators compared to macroeconomic counterparts in forecasting urea and DAP prices at the global level. Also, the price movements of urea and DAP are similar at the global level. On the contrary, macroeconomic indicators influence more at the local level. The CBOE volatility index for urea, geopolitical risk, and commodity industrial input for DAP significantly influence the price movements at the local level.