AI-Powered Demand Forecasting for Sustainable Supply Chains

Maradani, Kumar (2025) AI-Powered Demand Forecasting for Sustainable Supply Chains. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (632kB) | Preview

Abstract

This research presents a data-driven approach to forecasting weekly sales across Walmart stores using AI and statistical models. Motivated by the need for accurate demand prediction in dynamic retail environments, the study integrates historical sales, markdown events, store attributes, and economic indicators. Four models—Random Forest, XGBoost, LSTM, and ARIMA—were implemented and evaluated using metrics such as RMSE and R². The Random Forest model delivered the highest accuracy (R² = 0.9776), while XGBoost provided explainability via SHAP. Correlation and seasonal analyses underscored the influence of promotions and calendar effects. The findings support sustainable inventory planning and markdown optimization, fulfilling both predictive accuracy and interpretability goals. Future work recommends real-time deployment and deeper temporal learning for retail decision-making.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Siddig, Abubakr UNSPECIFIED
Uncontrolled Keywords:	Retail forecasting; AI models; Random Forest; XGBoost; ARIMA; LSTM; markdown analysis; SHAP interpretability
Subjects:	Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence 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:	26 Aug 2026 08:43
Last Modified:	26 Aug 2026 08:43
URI:	https://norma.ncirl.ie/id/eprint/9642

Actions (login required)

View Item