Title: Scenario-based multi-objective optimisation model based on supervised machine learning to configure a plastic closed-loop supply chain network

Authors: Sahand Ashtab; Babak Mohamadpour Tosarkani

Addresses: Shannon School of Business, Cape Breton University Sydney, Nova Scotia B1P 6L2, Canada ' School of Engineering, University of British Columbia Okanagan Campus, Kelowna, BC V1V 1V7, Canada

Abstract: Plastic recycling has received a lot of attention around the world. In this regard, a multi-objective optimisation model for plastic closed loop supply chain (CLSC) configuration is developed. Specifically, this paper simultaneously investigates the impact of adding washing machines to plastic recovery centres and corporations' role in consumer awareness on plastic recycling on plastic CLSC network configuration cost and carbon dioxide (i.e., CO₂) emissions. Our numerical results indicate that the combination of adding washing machines to recovery centres, and increased return of plastic products due of increased corporate responsibility in consumer awareness have the potential to contribute to both economic and environmental pillars of sustainability by decreasing the design cost, i.e., by 3.93%, and CO₂ emissions, i.e., by 14.24%. Furthermore, sensitivity analysis is conducted to consider the effects of unpredictable changes in demand and return. The implications of our study concerning social sustainability, policymakers, and municipalities are discussed.

Keywords: multi-objective optimisation; machine learning technique; logistic regression; corporate responsibility; closed loop supply chain; CLSC; plastic.

DOI: 10.1504/IJBPSCM.2023.130469

International Journal of Business Performance and Supply Chain Modelling, 2023 Vol.14 No.1, pp.106 - 128

Received: 27 Jan 2022
Accepted: 02 Aug 2022
Published online: 21 Apr 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article