The impact of the Covid-19 pandemic on key indicators of personnel security : a study with neural network technologies

Abstract

PURPOSE: The aim of this paper is to analyze the conceptual foundations of the use of artificial neural networks for highly accurate prediction of personnel security, construction of a mathematical model and building network architecture to solve the problem, as well as providing an example of forecasting and interpretation of results.

DESIGN/METHODOLOGY/APPROACH: Assessing the impact of the coronavirus disease (COVID19) pandemic caused by SARS-CoV-2 on all aspects of human civilization is an urgent scientific challenge today. However, it is already clear that it is human potential that will be impacted most by the pandemic. Using artificial neural networks with radial basis functions, the article predicts the influence of the COVID-19 pandemic on staff turnover, which is one of the most important indicators of personnel security.

FINDINGS: The network architecture is built and its mathematical description is made. The main factors influencing staff turnover as one of the main components of personnel security have been defined. Staff turnover in the EU in 2020 and its dependence on the GDP change value has been analyzed.

PRACTICAL IMPLICATIONS: Personnel security of enterprises and organizations is the basis of economic security nationwide. Nowadays, the Covid-19 pandemic first and foremost hits staff, especially their mental and physical health, thus having a direct impact on the level of personnel security. That is why, in order to effectively prevent a decline in the level of economic security, the impact of the pandemic on key personnel security indicators should be monitored in a timely manner. This is possible then using our metod.

ORIGINALITY/VALUE: The value of the research is to test the adequacy of the artificial neural network with RBF in predicting the impact of the COVID-19 pandemic on personnel security. It also offers testing the prognostic properties of this type of ANN and considers the possibility of their use for analysis, evaluation and forecasting of socio-economic phenomena and processes.