Exploring the impact of customer demographics and coupon redemption on the accuracy of XGBoost demand forecasting model

Mihaylova, Boryana (2025) Exploring the impact of customer demographics and coupon redemption on the accuracy of XGBoost demand forecasting model. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (645kB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Demand forecasting in the food and retail sector is essential for efficient supply chain management, yet it is a highly challenging task due to a variety of internal and external factors affecting demand. Promotions are one of the factors that complicate forecasting. Customer engagement is crucial for business growth and retailers must have a good understanding of their consumer base to tailor their marketing efforts accordingly. Customer demographics and coupon redemption data can be incorporated into the demand forecast to capture their effect. This paper investigates the impact of these data on model performance and compares a baseline XGBoost model with 9 features and an XGBoost model with 19 features, 10 of which are derived from demographic and promotional data. The enhanced model led to a drop of 10% in both RMSE and MAE and 18% reduction in MSE. Homeowner description and household composition ranked in top 10 predictive features. The findings have implications for both demand forecasting and marketing. Grocery retailers can achieve better forecast and reduce the risk of stockouts or overstocking by incorporating demographic and coupon data. The findings can be used to tailor marketing strategies to household profiles to further strengthen customer satisfaction and engagement.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hasanuzzaman, Mohammed UNSPECIFIED
Subjects:	H Social Sciences > HF Commerce > Marketing > Consumer Behaviour H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Food Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Retail Industry H Social Sciences > HD Industries. Land use. Labor > Business Logistics > Supply Chain Management
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	08 Sep 2026 10:26
Last Modified:	08 Sep 2026 10:26
URI:	https://norma.ncirl.ie/id/eprint/9884

Actions (login required)

View Item