Developing Supply Chain Risk Management Strategies by Using Counterfactual Explanation

被引:0
作者
Ordibazar, Amir Hossein [1 ]
Hussain, Omar [1 ]
Chakrabortty, Ripon K. [2 ]
Saberi, Morteza [3 ]
Irannezhad, Elnaz [4 ]
机构
[1] UNSW Canberra, Sch Business, Canberra, ACT, Australia
[2] UNSW Canberra, Sch Engn & Informat Technol, Canberra, ACT, Australia
[3] Univ Technol Sydney, Sch Comp Sci, Sydney, NSW, Australia
[4] UNSW Sydney, Sch Civil & Environm Engn, Kensington, NSW, Australia
来源
SERVICE-ORIENTED COMPUTING - ICSOC 2022 WORKSHOPS | 2023年 / 13821卷
关键词
Supply Chain Risk Management; Recommendations; Counterfactual Explanation; Optimisation; Case study;
D O I
10.1007/978-3-031-26507-5_5
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Supply Chain Risk Management (SCRM) is necessary for economic development and the well-being of society. Therefore, many researchers and practitioners focus on developing new methods to identify, assess, mitigate and monitor supply chain risks. This paper developed the Risk Management by Counterfactual Explanation (RMCE) framework to manage risks in Supply Chain Networks (SCNs). The RMCE framework focuses on monitoring SCN, and in case of any risks eventuating, it explains them to the user and recommends mitigation strategies to avoid them proactively. RMCE uses optimisation models to design the SCN and Counterfactual Explanation (CE) to generate mitigation recommendations. The developed approach is applied to an actual case study related to a global SCN to test and validate the proposed framework. The final results show that the RMCE framework can correctly predict risks and give understandable explanations and solutions to mitigate the impact of the monitored risks on the case study.
引用
收藏
页码:53 / 65
页数:13
相关论文
共 13 条
  • [1] Bajaj M, 2021, ADV NEUR IN, V34
  • [3] A supervised machine learning approach to data-driven simulation of resilient supplier selection in digital manufacturing
    Cavalcante, Ian M.
    Frazzon, Enzo M.
    Forcellini, Fernando A.
    Ivanov, Dmitry
    [J]. INTERNATIONAL JOURNAL OF INFORMATION MANAGEMENT, 2019, 49 : 86 - 97
  • [4] Gupta S., 2021, IEEE Transactions on Engineering Management
  • [5] XFDDC: eXplainable Fault Detection Diagnosis and Correction framework for chemical process systems
    Harinarayan, R. Rajesh Alias
    Shalinie, S. Mercy
    [J]. PROCESS SAFETY AND ENVIRONMENTAL PROTECTION, 2022, 165 : 463 - 474
  • [6] Kanamori K, 2020, PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, P2855
  • [7] Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
    Mothilal, Ramaravind K.
    Sharma, Amit
    Tan, Chenhao
    [J]. FAT* '20: PROCEEDINGS OF THE 2020 CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, 2020, : 607 - 617
  • [8] Exploring the role of artificial intelligence in managing agricultural supply chain risk to counter the impacts of the COVID-19 pandemic
    Nayal, Kirti
    Raut, Rakesh
    Priyadarshinee, Pragati
    Narkhede, Balkrishna Eknath
    Kazancoglu, Yigit
    Narwane, Vaibhav
    [J]. INTERNATIONAL JOURNAL OF LOGISTICS MANAGEMENT, 2022, 33 (03) : 744 - 772
  • [9] A Recommender System and Risk Mitigation Strategy for Supply Chain Management Using the Counterfactual Explanation Algorithm
    Ordibazar, Amir Hossein
    Hussain, Omar
    Saberi, Morteza
    [J]. SERVICE-ORIENTED COMPUTING, ICSOC 2021 WORKSHOPS, 2022, 13236 : 103 - 116
  • [10] FACE: Feasible and Actionable Counterfactual Explanations
    Poyiadzi, Rafael
    Sokol, Kacper
    Santos-Rodriguez, Raul
    De Bie, Tijl
    Flach, Peter
    [J]. PROCEEDINGS OF THE 3RD AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY AIES 2020, 2020, : 344 - 350