Artificial Intelligence (AI)-based Multi-criteria Shipping Industry Provider Selection

Khan, Ibraheem Abdulhafiz Q.

Artificial Intelligence (AI)-based Multi-criteria Shipping Industry Provider Selection

Khan, Ibraheem Abdulhafiz Q.

Permalink

Publication Type:: Thesis
Issue Date:: 2025

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (7.81 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Khan, Ibraheem Abdulhafiz Q.
dc.date.accessioned	2026-05-07T06:41:42Z
dc.date.available	2026-05-07T06:41:42Z
dc.date.issued	2025
dc.identifier.uri	http://hdl.handle.net/10453/194900
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	This thesis highlights that automating the selection of maritime shipping service providers is pivotal to supply-chain performance. By replacing fragmented and subjective practices with transparent analytics, automation reduces cost and time, improves reliability, and ensures decisions are reproducible at scale. To achieve this, the thesis introduces an intelligent multi-criteria search engine (MC-SE) that integrates artificial intelligence (AI) and multi-criteria decision-making (MCDM) to support both shippers and freight companies in identifying reliable, cost-effective providers. The objectives are to (i) develop an AI-based predictive classifier for offshore shipping decisions; (ii) systematically map provider criteria to the service quality framework (SERVQUAL); (iii) propose an AI-assisted approach for criteria weighting; (iv)conduct a SERVQUAL survey for provider-side assessment; and (v) validate the framework through an Australian case study. Methodologically, criteria were extracted from provider websites and benchmark datasets, then clustered into decision attributes using semantic similarity techniques. These clusters were aligned with SERVQUAL dimensions to ensure construct validity. AI-based weighting and supervised learning were applied within an MCDM pipeline to calculate attribute importance, integrate cost as a complementary decision factor, and rank providers objectively. This dual use of structured datasets and unstructured textual content ensures that the framework adapts to both traditional logistics data and dynamic, web-based information sources. Provider-side service quality is structured via SERVQUAL, while cost is modelled as a complementary decision attribute within the overall MC-SE multi-criteria framework. Validation demonstrates strong agreement between the proposed MC-SE weighting and the SERVQUAL survey (mean absolute error (MAE), MAE = 0.014), with dimension-level differences typically within 2–3%. The optimisation classifier, based on a voting ensemble, achieves 82.3% accuracy on held-out test data. These findings show that data-driven weighting, combined with supervised learning, can robustly support provider selection in practice. Overall, this thesis develops a novel, AI-driven framework to support the automated selection of maritime shipping service providers, bridging gaps between academic models and industry practice. Future research will refine the MC-SE framework, evaluate its portability across diverse contexts, and extend the evaluation to incorporate customer-experience evidence that complements provider-side quality and explicit cost trade-offs. Importantly, providers’ clusters are consistently aligned with canonical SERVQUAL dimensions to preserve theoretical and empirical coherence.	en_US.UTF-8
dc.format	Thesis (PhD)
dc.language.iso	en_US	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/194900/1/thesis.pdf
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	© 2025 Ibraheem Abdulhafiz Q. Khan
dc.rights	au.edu.uts.lib/cph
dc.title	Artificial Intelligence (AI)-based Multi-criteria Shipping Industry Provider Selection	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

This thesis highlights that automating the selection of maritime shipping service providers is pivotal to supply-chain performance. By replacing fragmented and subjective practices with transparent analytics, automation reduces cost and time, improves reliability, and ensures decisions are reproducible at scale. To achieve this, the thesis introduces an intelligent multi-criteria search engine (MC-SE) that integrates artificial intelligence (AI) and multi-criteria decision-making (MCDM) to support both shippers and freight companies in identifying reliable, cost-effective providers. The objectives are to (i) develop an AI-based predictive classifier for offshore shipping decisions; (ii) systematically map provider criteria to the service quality framework (SERVQUAL); (iii) propose an AI-assisted approach for criteria weighting; (iv)conduct a SERVQUAL survey for provider-side assessment; and (v) validate the framework through an Australian case study. Methodologically, criteria were extracted from provider websites and benchmark datasets, then clustered into decision attributes using semantic similarity techniques. These clusters were aligned with SERVQUAL dimensions to ensure construct validity. AI-based weighting and supervised learning were applied within an MCDM pipeline to calculate attribute importance, integrate cost as a complementary decision factor, and rank providers objectively. This dual use of structured datasets and unstructured textual content ensures that the framework adapts to both traditional logistics data and dynamic, web-based information sources. Provider-side service quality is structured via SERVQUAL, while cost is modelled as a complementary decision attribute within the overall MC-SE multi-criteria framework. Validation demonstrates strong agreement between the proposed MC-SE weighting and the SERVQUAL survey (mean absolute error (MAE), MAE = 0.014), with dimension-level differences typically within 2–3%. The optimisation classifier, based on a voting ensemble, achieves 82.3% accuracy on held-out test data. These findings show that data-driven weighting, combined with supervised learning, can robustly support provider selection in practice. Overall, this thesis develops a novel, AI-driven framework to support the automated selection of maritime shipping service providers, bridging gaps between academic models and industry practice. Future research will refine the MC-SE framework, evaluate its portability across diverse contexts, and extend the evaluation to incorporate customer-experience evidence that complements provider-side quality and explicit cost trade-offs. Importantly, providers’ clusters are consistently aligned with canonical SERVQUAL dimensions to preserve theoretical and empirical coherence.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/194900