Skip navigation

Exploring applications of big data analytics in supply chain management

Exploring applications of big data analytics in supply chain management

Nguyen, Truong Van (2019) Exploring applications of big data analytics in supply chain management. PhD thesis, University of Greenwich.

[img]
Preview
PDF
Truong Van Nguyen 2019 - secured.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (3MB) | Preview

Abstract

Empirical evidence demonstrates many benefits of Big data analytics (BDA) in supply chain management (SCM), including reduced operational costs, improved SC agility, and increased customer satisfaction. However, reports show that the BDA adoption of companies in SCM is relatively low, and the main reason for this is lack of understanding of how it can be implemented to address specific business problems.

Therefore, the aim of this thesis is to explore new applications of BDA to support the data-driven decision making in SCM. Particularly, the thesis addresses four research objectives: (1) to conduct a literature review that summarises what and how BDA has been applied within the SCM context. As a result, several research gaps are revealed, which leads to future research directions; (2) to develop a comprehensible, data-driven demand prediction of remanufactured products. Validated with a real-world Amazon dataset, the result shows that the proposed approach can produce a highly accurate and robust prediction of product demand, as well as providing insights into the non-linear effect of online market factors on demand; (3) to develop a prescriptive price optimisation model by extending the proposed demand prediction with a mixed integer linear programme to optimise promotional pricing decisions. The result shows that the obtained optimal promotional price solution could increase both sales and revenue; (4) Finally, the thesis proposes a data-driven prescriptive approach for large-scale optimisation problems, based on the hybrid approach combining association rule mining and complex network theory. For validation, the proposed model is applied to optimise the large-scale dry port location problems in Mainland China in the context of the Belt and Road Initiatives (BRI). The dry port solution obtained from the model is realistic and applicable as it accurately pinpoints key locations in the real BRI development plans.

The contribution of this thesis is multifaceted. Theoretically, the thesis serves as a good starting point for researchers to build up the foundation of BDA, which enables to develop a machine learning-based approach to tackle the established research problems. Practically, the thesis facilitates the data-driven decision making across industries such as online marketing strategy development for remanufactured products, daily promotional planning for retailers, and logistics network design for dry port planners.

Item Type: Thesis (PhD)
Uncontrolled Keywords: big data analytics; data driven demand; supply chain management;
Subjects: H Social Sciences > H Social Sciences (General)
Faculty / Department / Research Group: Faculty of Business
Faculty of Business > Department of Systems Management & Strategy
Last Modified: 28 Feb 2020 17:45
Selected for GREAT 2016: None
Selected for GREAT 2017: None
Selected for GREAT 2018: None
Selected for GREAT 2019: None
URI: http://gala.gre.ac.uk/id/eprint/27178

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics