Explainability Analysis of the Evaluation Model of the Level of Digital Transformation in MSMEs based on Fuzzy Cognitive Maps

Explainability Analysis on Fuzzy Cognitive Maps

Authors

  • Jose Aguilar Universidad de los Andes, Venezuela
  • Jairo Fuentes Universidad Francisco de Paula Santander
  • Edwin Montoya
  • William Hoyos
  • Diego Benito

DOI:

https://doi.org/10.19153/cleiej.27.2.2

Keywords:

Digital Transformation, Fuzzy Cognitive Maps, Explainability Analysis, Machine Learning

Abstract

the concept of digital transformation involves exploiting digital technologies to generate new ways of doing things in organizations, including the creation of new processes, models, and services that produce value based on the digitization of data and processes. The application of digital technologies enables organizations to develop capabilities for innovation, automation, etc., utilizing both established and emerging technologies, including the widespread use of artificial intelligence. This article proposes the implementation of Fuzzy Cognitive Maps (FCMs) based on experts and data for the evaluation of the level of digital transformation in MSMEs (Micro, Small and Medium Enterprises). Additionally, this work carries out an explainability analysis of the evaluation models based on FCMs. The main digital transformation variables used to define our FCMs were classified into five groups, based on the COBIT standard: i) Organization and Culture variables related to strategies, way of working, and ecosystems, ii) Customer variables related to services and digital channels and products, iii) Operations and Internal Processes variables related to supply chain, suppliers, and business model, iv) Information Technologies variables related to innovation, digitization, data and analytic. Finally, the fifth type of variable is the target, which indicates the level of digital transformation of the organization. Our model managed to specify with 99.4% the level of digital transformation of the organization. Furthermore, the explanatory capacity of the FCMs developed in this work was explored using different explainability methods, some general and others specific to the FCMs. In general, the results obtained in the work are very encouraging since the quality metrics obtained with the evaluation models are very good, almost always higher than 90%; and the explanations obtained with the explainability methods allow for an in-depth analysis of the behavior of the variables in the results obtained, something very important to understand how to improve the levels of digital transformation in organizations.

References

M. Bach, M. Spremi?, D. Vugec, “Integrating Digital Transformation Strategies into Firms: Values, Routes and Best Practice Examples,” Manag. Technol. Challenges Digit. Age, pp. 107–128, 2018, doi: 10.1201/9781351238922-5.

G. Nápoles, M. L. Espinosa, I. Grau, K. Vanhoof, “FCM Expert: Software Tool for Scenario Analysis and Pattern Classification Based on Fuzzy Cognitive Maps,” Int. J. Artif. Intell. Tools, vol. 27, no. 7, 2018, doi: 10.1142/S0218213018600102.

W. Hoyos, J. Aguilar, M. Toro, “A clinical decision-support system for dengue based on fuzzy cognitive maps,” Health Care Manag. Sci., vol. 25, no. 4, pp. 666–681, 2022, doi: 10.1007/s10729-022-09611-6.

I. Bolaños-Portilla, I. Hurtado-Sánchez, I. Restrepo-Tarquino, “Diffuse cognitive maps for analysis of vulnerability to climate variability in andean rural micro-watersheds,” DYNA, vol. 87, no. 212, pp. 38–46, 2020, doi: 10.15446/dyna. v87n212.79943.

A. Hosseini, J. Heidary, J. Antucheviciene, M. Azari, S. Razavi, “Supplier selection in the industry 4.0 era by using a fuzzy cognitive map and hesitant fuzzy linguistic VIKOR methodology,” Environ. Sci. Pollut. Res., 2023, doi: 10.1007/s11356-023-26004-6.

N. Yuliantari, N. Pramuki, “The Role of Competitive Advantage in Mediating the Relationship Between Digital Transformation and MSME Performance in Bali,” J. Ekon. Bisnis Jagaditha, vol. 9, no. 1, pp. 66–75, 2022, doi: 10.22225/jj.9.1.2022.66-75.

E. Gökalp, V. Martinez, “Digital transformation maturity assessment: development of the digital transformation capability maturity model,” Int. J. Prod. Res., vol. 60, no. 20, pp. 6282–6302, 2022, doi: 10.1080/00207543.2021.1991020.

T. Aguiar, S. Gomes, P. Da Cunha, M. Da Silva, “Digital transformation capability maturity model framework,” in Proc. IEEE 23rd Int. Enterp. Distrib. Object Comput. Conf., pp. 51–57, 2019, doi: 10.1109/EDOC.2019.00016.

V. Veldhoven, J. Vanthienen," Designing a Comprehensive Understanding of Digital Transformation and its Impact". In proc. Bled eConference. 2019.

D. Sen, M. Ozturk, O. Vayvay, “An Overview of Big Data for Growth in SMEs,” Procedia - Soc. Behav. Sci., vol. 235, pp. 159–167, 2016, doi: 10.1016/j.sbspro.2016.11.011.

L. Morales Escobar, J. Aguilar, A. Garcés-Jiménez, J. Gutierrez De Mesa, J. Gomez-Pulido, “Advanced Fuzzy-Logic-Based Context-Driven Control for HVAC Management Systems in Buildings," IEEE Access, vol. 8, pp. 16111-16126, 2020, doi: 10.1109/ACCESS.2020.2966545.

A. Singh, T. Hess, “How chief digital officers promote the digital transformation of their companies,” Mis. Exec., vol. 16, no. 1, pp. 1–17, 2017, doi: 10.4324/9780429286797-9.

A. Margiono, “Digital transformation: setting the pace,” J. Bus. Strategy, vol. 42, no. 5, pp. 315–322, 2020, doi: 10.1108/JBS-11-2019-0215.

B. Kosko, “Fuzzy cognitive maps,” International Journal of Man-Machine Studies, vol. 24, no. 1. pp. 65–75, 1986, doi: 10.1016/S0020-7373(86)80040-2.

J. Aguilar, “A fuzzy cognitive map based on the random neural model,” Lect. Notes in Comput. Sci., vol. 2070, pp. 333–338, 2001, doi: 10.1007/3-540-45517-5_37.

G. Nápoles, I. Grau, L. Concepción, L. Koutsoviti Koumeri, J. Papa, “Modeling implicit bias with fuzzy cognitive maps,” Neurocomputing, vol. 481, pp. 33–45, 2022, doi: 10.1016/j.neucom.2022.01.070.

G. Xirogiannis, M. Glykas, C., Staikouras “Fuzzy Cognitive Maps in Banking Business Process Performance Measurement". In Fuzzy Cognitive Maps. Studies in Fuzziness and Soft Computing (Glykas M. ed.), Springer, pp. 161–200, 2010.

H. Sánchez, J. Aguilar, O. Terán, J. Gutiérrez de Mesa, "Modeling the process of shaping the public opinion through Multilevel Fuzzy Cognitive Maps", Applied Soft Computing, vol. 85, 2019, doi: 10.1016/j.asoc.2019.105756.

J. Salmeron, S. Rahimi, A. Navali, A. Sadeghpour "Medical diagnosis of Rheumatoid Arthritis using data driven PSO-FCM with scarce datasets". Neurocomputing, pp.:104–112. 2017, doi: 10. 1016/j. neucom. 2016. 09. 113.

J. Waissman, R. Sarrate, T. Escobet, J. Aguilar, B. Dahhou, "Wastewater treatment process supervision by means of a fuzzy automaton model", In Proc IEEE International Symposium on Intelligent Control, pp. 163-168, 2000, doi: 10.1109/ISIC.2000.88291.

N. Perozo, J. Aguilar, O. Terán and H. Molina, "A Verification Method for MASOES," IEEE Transactions on Cybernetics, vol. 43, no. 1, pp. 64-76, 2013, doi: 10.1109/TSMCB.2012.2199106.

J. Aguilar, J. Contreras. “The FCM Designer Tool”. In Fuzzy Cognitive Maps. Studies in Fuzziness and Soft Computing (Glykas M. ed.), Springer, pp. 71–87, 2010, doi: 10.1007/978-3-642-03220-2_4.

J. Aguilar, I. Bessembel, M. Cerrada, F. Hidrobo, F. Narciso, “Una Metodología para el Modelado de Sistemas de Ingeniería Orientado a Agentes", Revista Iberoamericana de Inteligencia Artificial, vol. 12, no. 38, pp.39-60, 2008.

M. Sánchez, J. Aguilar, J. Cordero, P. Valdiviezo-Díaz, L. Barba-Guamán, L. Chamba-Eras, “Cloud Computing in Smart Educational Environments: Application in Learning Analytics as Service”. In: New Advances in Information Systems and Technologies (Rocha, Á., Correia, A., Adeli, H., Reis, L., Mendonça Teixeira, M., eds.), vol. 444. Springer, pp. 993–1002, 2016.

J. Aguilar, “Multilayer Cognitive Maps in the Resolution of Problems using the FCM Designer Tool”, Applied Artificial Intelligence, vol. 30, no. 7, pp. 720-743, 2016.

G. Csardi, T. Nepusz, “The igraph software package for complex network research,” InterJournal Complex Syst., no. 1695, 2006.

R. Axelrod, “Structure of decision: The cognitive maps of political elites”. Princeton University Press, 1976.

W. Stach, L. Kurgan, W. Pedrycz and M. Reformat, "Genetic learning of fuzzy cognitive maps", Fuzzy Sets Syst., vol. 153, no. 3, pp. 371-401, 2005.

C. Murungweni, M. van Wijk, JA. Andersson, E. Smaling, and K. Giller. “Application of fuzzy cognitive mapping in livelihood vulnerability analysis”. Ecology and Society, vol. 16, no. 4, 2011.

A. Al Farsi, D. Petrovic, and F. Doctor. “A non-iterative reasoning algorithm for fuzzy cognitive maps based on type 2 fuzzy sets”. Information Sciences, vol. 622, pp. 319–336, 2023.

F. Aghaeipoor, M. Sabokrou, and A. Fernandez. “Fuzzy rule-based explainer systems for deep neural networks: From local explainability to global understanding”. IEEE Transactions on Fuzzy Systems, vol. 31, no 9, pp. 3069–3080, 2023.

M. Ribeiro, S. Singh, and C. Guestrin. ”Why Should I Trust You?”: Explaining the Predictions of Any Classifier”. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144. 2016.

X. Mi, B. B. Zou, F. Zou. “Permutation-based identification of important biomarkers for complex diseases via machine learning models”. NatCommun, vol. 12, 2022.

D. Benito, C. Quintero, J. Aguilar, J. M. Ramírez and A. Fernández Anta “Explainability Analysis: An In-Depth Comparison between Fuzzy Cognitive Maps and LAMDA”, submitted to publication, 2024.

I. Apostolopoulos, P. Groumpos, “Fuzzy Cognitive Maps: Their Role in Explainable Artificial Intelligence. Appl. Sci. vol. 12, 2023, https://doi.org/10.3390/app13063412.

G. Nápoles, N. Rankovi?, Y. Salgueiro, “On the interpretability of Fuzzy Cognitive Maps”, Knowledge-Based Systems, vol. 281, 2023.

M. Tyrovolas, X. Liang, C. Stylios, C. “Information flow-based fuzzy cognitive maps with enhanced interpretability”. Granul. Comput. vol. 8, pp. 2021–2038, 2023.

F. Hoitsma, A. Knoben, M. Espinosa, G. Nápoles, “Symbolic Explanation Module for Fuzzy Cognitive Map-Based Reasoning Models”. Lecture Notes in Computer Science, vol 12498. pp 21–34, Springer, 2020. https://doi.org/10.1007/978-3-030-63799-6_2

T. Mansouri, S. Vadera, “Explainable fault prediction using learning fuzzy cognitive maps”. Expert Systems, vol. 40, no. 8, pp. e13316, 2023.

Y. Wei and B. Jiang, "Interpretable Cognitive State Prediction via Temporal Fuzzy Cognitive Map," IEEE Transactions on Learning Technologies, vol. 17, pp. 514-526, 2024.

Departamento Administrativo Nacional de Estadística, “Colombia - Encuesta de Desarrollo e Innovación Tecnológica - EDIT - Industria 2017 - 2018”, [Online]. Available: http://microdatos.dane.gov.co/index.php

Downloads

Published

2024-07-21

Issue

Vol. 27 No. 2 (2023): CLEI 2023 best papers Vol. I

Section

Articles

License

Copyright (c) 2024 Jose Aguilar, Jairo Fuentes, Edwin Montoya, William Hoyos, Diego Benito

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

CLEIej is supported by its home institution, CLEI, and by the contribution of the Latin American and international researchers community, and it does not apply any author charges whatsoever for submitting and publishing. Since its creation in 1998, all contents are made publicly accesibly. The current license being applied is a (CC)-BY license (effective October 2015; between 2011 and 2015 a (CC)-BY-NC license was used).