An XGBoost-Based Forecasting Framework for Product Cannibalization

TL;DR

This paper introduces a three-stage XGBoost framework for demand forecasting that effectively handles product cannibalization and long-term prediction challenges, outperforming standard XGBoost methods especially with limited training data.

Contribution

The paper proposes a novel three-stage XGBoost-based framework specifically designed to address product cannibalization and long-term forecasting issues, improving prediction accuracy.

Findings

The three-stage XGBoost framework outperforms regular XGBoost in forecasting accuracy.

The method effectively mitigates long-term error propagation.

The approach is particularly effective with small training datasets.

Abstract

Two major challenges in demand forecasting are product cannibalization and long term forecasting. Product cannibalization is a phenomenon in which high demand of some products leads to reduction in sales of other products. Long term forecasting involves forecasting the sales over longer time frame that is critical for strategic business purposes. Also, conventional methods, for instance, recurrent neural networks may be ineffective where train data size is small as in the case in this study. This work presents XGBoost-based three-stage framework that addresses product cannibalization and associated long term error propagation problems. The performance of the proposed three-stage XGBoost-based framework is compared to and is found superior than that of regular XGBoost algorithm.