It was very difficult to predict the global pandemic caused by the new coronavirus COVID-19 disease that spread around the world. There is no doubt that the pandemic will have a serious impact on worldwide economy because besides causing a health crisis, the pandemic threatens to generate an economic and financial crisis. Therefore, the management of service providing entities were faced with a challenge of finding a model to perform their business activities and take care of the employees' health at the same time. This paper discusses possible solutions related to internal audit as a service providing profession. The research findings in the field have led to the conclusion that auditors can take advantage of this business environment to undergo complete digital transformation and make extensive use of remote auditing, since the function of internal audit can be further improved by using new information and communication technologies. The results of the research, which was focused on the opinions of certified internal auditors from the Republic of Serbia, showed that the advantages of remote auditing in internal audit outweighed the disadvantages. During the pandemic, the quality level of performed audits either increased or stayed the same, as well as the level of trust of audit client management, whereas savings in time and a decrease of travel-related costs were substantial.
The aim of this paper is to present corporate default prediction models constructed in the specific market conditions that prevail in the Republic of Serbia, and to compare their prediction accuracy with the most frequently used model - Altman's Z-score. Many authors have constructed models for the purpose of bankruptcy prediction, but predominantly in stable market conditions or in times of economic growth. We have presented three models that use standard ratios and some specific variables in order to predict corporate bankruptcy in emerging and distressed markets. For that purpose, we have used the following statistical and machine learning methods on a training sample (130 companies): Logistic Regression, Decision Trees and Artificial Neural Networks. Finally, we have compared accuracies of predictions of our models to those of the Altman's Z-score models using an independent hold-out sample (102 companies). Results show that, out of the aforementioned three models, only the one relying on the artificial neural network algorithm performs better when applied on the hold-out sample, compared to Altman's Z-score models.