NORMA eResearch @NCI Library

Demand Forecasting based on External Factors using Clustering and Machine learning

Paruthipattu, Sruthi Prabakaran (2021) Demand Forecasting based on External Factors using Clustering and Machine learning. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (767kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


Forecasting time series data is challenging when multiple factors are taken into account. The retail industry is one such where multiple factors play an important role. And it is important to maintain the supply chain processes. At different levels of the supply chain, various factors influence the demand creating a dependency. Factors like weather, promotion, holiday, etc create a huge impact on the demand for a few to multiple products. And these factors may influence retail differently based on the location, event, economic crisis, etc. Decision-makers like the CEO, logistics manager, Branch managers, etc will make use of this data in taking impactful decisions and these affect the retailers, production engineers, suppliers, etc indirectly. This research aims to see on what scale some of these factors affect the demand for products in clusters of stores that are related in different aspects using hierarchical clustering. To forecast demand within the identified clusters, ensemble models like random forest and XGBoost is used. A relatively new combinational model of univariate LSTM and RF is also implemented based on previous work. Out of all three models, XGBoost performed well in terms of RMSE and MAE and the results were visualized using the SHAP library. This research is unique in terms of considering partial new store data, macroeconomic factors: oil price, and the influence of these factors along with other factors on different clusters of stores.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
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: Tamara Malone
Date Deposited: 27 Feb 2023 17:06
Last Modified: 01 Mar 2023 17:53

Actions (login required)

View Item View Item