Application of Explainable Artificial Intelligence technique to model the predictors of South African SMMEs resilient performance during the Covid-19 pandemic

Abstract

Various studies have been carried out to establish the key drivers impacting small enterprise sustainable performance in developing countries. Despite many policy-oriented studies to uncover the factors influencing SME resilience in emerging markets, these firms continue to register high failure rate, which has been further exacerbated by the Covid-19 pandemic. Guided by a history of linear- and log-linear econometric model estimation that ignores potential network effects, our study extends the literature by implicating SMME resilience as a production network. Utilising data from both incubated and non-incubated SMMEs, marking a departure from traditional linear econometric models, radial basis function artificial neural network algorithm was invoked to establish the drivers of SMME resilience during Covid-19 regime. The study extends the literature by implicating eXplainable Artificial Intelligence (XAI) methods. Specifically, optimal SHapley Additive Explanations values (SHAP values) were computed to enhance the prediction output from the machine learning algorithm. The XAI analytics provide insightful findings on the key drivers which influenced the resilience of SMMEs during the Covid-19 pandemic. The importance of innovation through introduction of new products, company age and higher number of marketing mediums is confirmed however total assets, analytics, educational level and number of workers surfaced as a threat to these enterprises’ sustainable performance. The study recommends that both the government and SMEs should leverage XAI to identify their heterogeneous attributes and inform intelligent decision-making which necessities their resilient performance.

Keywords: {'name': 'Artificial Neural Networks, Covid-19, Explainable Artificial Intelligence, SMME Resilience, SHAP Values'}

Authors & affiliations

Helper Zhou
Affiliation not supplied

Lucy T Chamba
Affiliation not supplied

Robert. W. D Zondo
Affiliation not supplied

Deposited references

Supplied references, not a list of publications citing this article.

DOI: 10.1186/s13731-021-00156-6

DOI: 10.1007/s10796-022-10250-z

DOI: 10.47246/CEJGSD.2020.2.1.4

DOI: 10.1007/s11187-006-9002-5

DOI: 10.1596/1813-9450-5799

Bhatt, N. J. (2014). Productivity in small and medium enterprises of India: A Cobb-Douglas production function approach. IUP Journal of Management Research, 13(1), 29.

DOI: 10.1080/13669877.2020.1756379

Buyinza, F. (2011). Performance and Survival of Ugandan Manufacturing firms in the context of the East African Community. Economic Policy Research Centre (EPRC). Available: https://ideas.repec.org/p/ags/eprcrs/150477.html (Accessed 25 May 2019).

DOI: 10.1177/0149206317699521

DOI: 10.4102/sajems.v21i1.1726

DOI: 10.5539/ibr.v3n4p119

DOI: 10.1007/978-3-662-43917-3

EUROSTAT. (2018). Structural Business Statistics & Global Business Activities. (Retrieved on November 2022).

Farahani, D. S., Momeni, M., & Amiri, N. S. (2016). Car sales forecasting using artificial neural networks and analytical hierarchy process. Data Analytics: 69.

Garatsa, C., & Dlamini, B. (2021). Factors Influencing the Adoption and Implementation of Customer Relationship Management Strategies by Small and Medium Enterprises in KwaZulu-Natal. International Journal of Entrepreneurship, 25, 1-18.

DOI: 10.1080/00472778.2023.2193230

DOI: 10.1186/s40497-019-0183-1

Kajiji, N., & Dash, G. H. (2012). Efficient multiple objective neural network mapping of state-wide high school achievement. Journal of Applied Operational Research, 4(3), 139-151.

Kajiji, N., & Dash, G. H. (2012). Efficient multiple objective neural network mapping of state-wide high school achievement. Journal of Applied Operational Research, 4(3), 139-151.

Kajiji, N., & Dash, G., H. (2013). On the behavioral specification and multivariate neural network estimation of cognitive scale economies. Journal of Applied Operational Research, 5(1), 30.

DOI: 10.3390/risks7010029

DOI: 10.1016/j.eap.2022.09.006

DOI: 10.1016/S2212-5671(14)00634-0

DOI: 10.14257/ijunesst.2015.8.4.15

DOI: 10.1080/135048500416012

DOI: 10.1177/0894486513504434

DOI: 10.21511/ppm.19(2).2021.16

DOI: 10.1515/erj-2017-0030

DOI: 10.5465/amp.2013.0025

Obaid, O. I., Mohammed, M. A., Ghani, M., Mostafa, A., & Taha, F. (2018). Evaluating the performance of machine learning techniques in the classification of Wisconsin Breast Cancer. International Journal of Engineering & Technology, 7(4.36), 160-166.

DOI: 10.1108/JEEE-05-2020-0111

DOI: 10.3390/su13126628

DOI: 10.1016/j.jclepro.2018.12.199

DOI: 10.1108/IJOA-06-2017-1182

DOI: 10.1002/smj.640

DOI: 10.1561/111.00000005

DOI: 10.1007/s10462-018-9637-z

DOI: 10.1177/1476127018765031

Zhou, H. (2022). The influence of key risk drivers on the performance of SMMEs in the manufacturing sector in KwaZulu-Natal. PhD, Durban University of Technology.

DOI: 10.31920/2634-3649/2021/v11n1a1

DOI: 10.23962/10539/31371

DOI: 10.2139/ssrn.3310145