Proceedings of the 9^th International Conference on Operations and Supply Chain Management, Vietnam, 2019

Luh Putu Eka Yani
Sampoerna University

I Made Alan Priyatna
Faculty of Engineering & Technology, Sampoerna University

Ammar Aamer
Faculty of Engineering & Technology, Sampoerna University

In the current technological era, the rise of disruptive innovations is affecting the way industries run their operations. The disruptive impact of digitalization processes and the highly constant growth of sensible data are changing the very fabric of supply chain management. Disruptive technology offers innovative ways to tackle some of the main traditional approaches in the supply chain. Machine learning, which is viewed as disruptive technology, recently has evolved rapidly to optimize the process and efficiency in supply chain management. Machine learning could be applied in several stages of supply chain management from planning to the distribution process. In this paper, we explored and examined the literature of multiple machine learning algorithms and their application in the supply chain management, focusing on the demand forecasting stage since this the first and most important step of supply chain management. A total of 57 articles related to machine learning and demand forecasting were retrieved from ScienceDirect, Taylor and Francis, and Emerald databases. The result showed that the machine learning algorithm performs better than the traditional demand forecasting model. Moreover, neural network and support vector regression algorithms are among the most potential and applicable algorithms to implement in demand forecasting. The practical implication of this paper is in exposing the current machine learning issues in the industry to help stakeholders and decision-makers better plan corrective actions.

[Download Full Paper] [Bibtex]

The persistent DOI of this article will be available soon .