Publicação
Gen-AI and the Future of Supply Chain Management: The Impact of Large Language Models on Modern Supply Chain Management
| datacite.subject.fos | Ciências Naturais::Ciências da Computação e da Informação | pt_PT |
| dc.contributor.advisor | Bação, Fernando José Ferreira Lucas | |
| dc.contributor.author | Morales, Alex Adrian Santander | |
| dc.date.accessioned | 2024-11-14T12:12:59Z | |
| dc.date.available | 2024-11-14T12:12:59Z | |
| dc.date.issued | 2024-10-31 | |
| dc.description | Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data Science | pt_PT |
| dc.description.abstract | LLMs like GPT-4 possess an exceptional ability to understand and generate human language, driven by advancements in Artificial Intelligence, Deep Learning, and Natural Language Processing. Companies are increasingly interested in integrating this cutting-edge technology into their Supply Chain processes to leverage its capabilities. While previous studies have explored the impact of LLMs on various Supply Chain Management functions—such as demand forecasting, supplier evaluation, simulation, and optimization—no comprehensive survey has yet consolidated these functions into a single research effort. This thesis provides a thorough review of the impact of LLMs on Supply Chain Management, focusing on four key dimensions: demand forecasting, supplier evaluation, simulation, and optimization. The study begins with a knowledge background section designed to equip the reader with essential information about LLMs and Supply Chain Management. Following this, the benefits and challenges of applying LLMs in Supply Chain Management are examined, supported by two detailed case studies showcasing real-world applications. The thesis concludes by outlining potential directions for future research, offering a roadmap for further exploration in this rapidly evolving field. Key findings reveal that LLMs significantly enhance SCM by improving efficiency, accuracy, and decision-making capabilities. They empower both technical and non-technical users and democratize access to complex processes like simulations and optimization. However, integrating LLMs into SCM presents challenges such as user adoption issues, hallucinations, privacy concerns, and potential disruptions. Addressing these challenges is crucial for the successful and safe implementation of LLMs in SCM, paving the way for innovative, resilient, and responsive supply chain operations. | pt_PT |
| dc.identifier.tid | 203784359 | pt_PT |
| dc.identifier.uri | http://hdl.handle.net/10362/175206 | |
| dc.language.iso | eng | pt_PT |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | pt_PT |
| dc.subject | Large Language Models | pt_PT |
| dc.subject | Supply Chain Management | pt_PT |
| dc.subject | Generative Artificial Intelligence | pt_PT |
| dc.subject | Decision-Making | pt_PT |
| dc.subject | SDG 9 - Industry, innovation and infrastructure | pt_PT |
| dc.subject | SDG 12 - Responsible production and consumption | pt_PT |
| dc.title | Gen-AI and the Future of Supply Chain Management: The Impact of Large Language Models on Modern Supply Chain Management | pt_PT |
| dc.type | master thesis | |
| dspace.entity.type | Publication | |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | masterThesis | pt_PT |
| thesis.degree.name | Mestrado em Ciência de Dados e Métodos Analíticos Avançados, especialização em Ciência de Dados | pt_PT |