Lopatin Artem, PhD-student of Petro Mohyla Black Sea National University

ORCID ID: 0000-0002-2707-9033
e-mail: areterik@gmail.com

Use of Rough Set Theory and Neural Networks Methods in Supply Chain Management

Annotation. Introduction The decision to align a specific order with a supplier depends on a no of criteria. Generally the buyer’s decision depends on his assessment of the supplier’s ability to meet the criteria of quality, volume, terms of delivery, price and service. But to evaluate these criteria, the company needs to manage information from different sources through whole supply chain. One way to control may comprise artificial intelligence methods.

The main purposes of this article are to identify the AI subsectors that are most suitable for SCM programs, and characterize other subsectors in terms of their usefulness for improving SC performance. Synthesize the existing research on the appliance of rough set theory and neural networks methods touching SCM, on their practical implications and technical merits. Summarize research trends in rough set theory and neural networks methods and identify potential utilization of SCM that haven’t yet been studied in Ukrainian science field. Justify future prospects for expanding existing AI literature and unused AI research in Ukrainian science field topics related to SCM.

Results The article identifies the sub-sectors of artificial intelligence that are most suitable for supply chain management programs, and describes other sub-sectors in terms of their usefulness for improving the efficiency of supply chain management. Synthesize the existing literature on the appliance of rough set theory and neural networks methods in supply chains, on their practical implications and technical merits. The tendencies of researches of rough set theory and neural networks methods are generalized and potential spheres of their appliance in management of supply chains which haven’t been investigated yet are defined.

Conclusions. Despite the long history of AI, the potential of AI as a means of solving complex issues and finding info in the field of SC hasn’t been fully used in the past especially in the Ukrainian scientific literature. In particular, some groups of AI technologies, such as expert systems and GAs, are increasingly used to solve management issues, including inventory management, procurement, location planning, shipment coordination between contractors, and routing / planning issues. Further study of the issue requires consideration of the use of other AI methods in supply chain management, such as fuzzy logic and agent modeling and recognition of their practical aspects.

Keywords: artificial intelligence; supply chain management; rough sets; artificial neural networks.

References:

1. Nilsson, N. J. (1982). Principles of artificial intelligence. Los Altos, CA: Morgan Kaufmann Publishers, 1. 476.
2. Russell, S. & Norvig, P. (1995). Artificial intelligence: a modern approach. Upper Saddle River, NJ: Prentice-Hall.
3. Luger, G. F. (2002). Artificial intelligence: structures and strategies for complex problem solving. 4th ed. Pearson Education Limited, England: Essex.
4. Min, H. (2010). Artificial intelligence in supply chain management: Theory and applications. International Journal of Logistics-research and Applications, 13, 13-39. DOI: 10.1080/1367556090273.
5. Linde, H. & Schweizer, I. (2019). A White Paper on the Future of Artificial Intelligence, 1-10. DOI: 10.13140/RG.2.2.32564.19844.
6. Perrault, R., Shoham, Y., Brynjolfsson, E., Clark, J., Etchemendy, J. Grosz, B., Lyons, T., Manyika, J., Mishra, S. & Juan Carlos Niebles (2019). The AI Index 2019 Annual Report, AI Index Steering Committee. Stanford, CA: Human-Centered AI Institute, Stanford University.
7. Min, H. & Yu, W. (2008). Collaborative planning, forecasting and replenishment: demand planning in supply chain management. International Journal of Information Technology and Management, 7 (1), 4-20.
8. Bre, F. & Gimenez, J. & Fachinotti, V. (2017). Prediction of wind pressure coefficients on building surfaces using Artificial Neural Networks. Energy and Buildings, 158. DOI: 10.1016/j.enbuild.2017.11.045.
9. McCulloch, W.S. & Pitts, W. (1943). A logical calculus of the idea imminent in nervous activity. Bulletin of Mathematical Biophysics, 5, 115-137. DOI: 10.1007/BF02478259.
10. Pomerleau, D. A. (1993). Neural network perception for mobile robot guidance. Dordrecht, The Netherlands: Kluwer.
11. AlMana, A. & Aksoy, M. (2014). An Overview of Inductive Learning Algorithms. International Journal of Computer Applications, DOI: 10.5120/15340-3675.
12. Gaafar, L. K. & Choueiki, M. H. (2000). A neural network for solving the lot-sizing problem. Kuwait: Omega, The International Journal of Management, 28, 175-184.
13. Rohde, J. (2004). Hierarchical supply chain planning using artificial neural networks to anticipate base-level outcomes. OR Spectrum, 26. 471-492. DOI: 10.1007/s00291-004-0170-x.
14. Pawlak, Z. (1982). Rough sets. International Journal of Computer and Information Science, 11, 341-356. DOI: 10.1007/BF01001956.
15. Roy, P. & Goswami, S. & Chakraborty, S. & Azar, A. & Dey, N. (2014). Image Segmentation Using Rough Set Theory: A Review. Hershey, PA, USA: International Journal of Rough Sets and Data Analysis, 1, 62-74. DOI: 10.4018/ijrsda.2014070105.
16. Qinghua, Zh., Qin, X. & Guoyin, W. (2016) A survey on rough set theory and its applications. China: CAAI Transactions on Intelligence Technology, 1, 4, 323-333. DOI: 10.1016/j.trit.2016.11.001.
17. Pawlak, Z. (1984). Rough classification. International Journal of Man-Machine Studies, 72, 469-483. DOI: 10.1016/0377-2217(94)90415-4.
18. Pawlak, Z. (1989). Knowledge, reasoning and classification – a rough set perspective. Bulletin of the European Association for Theoretical Computer Science, 38, 199-210.
19. Pawlak, Z. (1997). Rough set approach to knowledge-based decision support. European Journal of Operational Research, 293 (3), 1-10. DOI: doi.org/10.1016/S0377-2217(96)00382-7.
20. Li, G. D., Yamaguchi, D. & Nagai, M. (2007). Application of grey-based rough decision-making approach to supplier selection. Journal of Modelling in Management, 2 (2), 131-142. DOI: 10.1108/17465660710763416.
21. Zheng, P. & Lai, K. K. (2008). A rough set approach on supply chain dynamic performance measurement. Springer, Berlin, Heidelberg: Lecture Notes in Computer Science, 4953, 312-322. DOI: 10.1007/978-3-540-78582-8_32.
22. Hrytsenko, V. I. (2016). Use Big Data tools to increase the effectiveness of online advertising. Ekonomiko-matematychne modeliuvannia sotsialno-ekonomichnykh system, 21, 5-21. Retrieved from: http://nbuv.gov.ua/UJRN/emmses_2016_21_3.
23. Zernjuk, V. (2015). Supply chain management. Ekonomičnyj forum, 4, 251-258. Retrieved from: http://nbuv.gov.ua/UJRN/ecfor_2015_4_41 [in Ukrainian].
24. Mozolevsʹka, O. & Stavycʹkyj, O. V. (2017). Use of neural networks for forecasting in the financial sphere. Aktualʹni problemy ekonomiky ta upravlinnja. Retrieved from: https://ela.kpi.ua/handle/123456789/22609 [in Ukrainian].
25. Novikova, O. V. (2014). Forecasting the gross domestic product based on the apparatus of artificial neural networks. Ekonomika i upravlinnja APK, 1, 5-11 [in Ukrainian].