Predicting the financial performance of a company (Chrome Nickel) in three scenarios during macroeconomic crises: A machine learning-based approach
Predicting the financial performance of a company (Chrome Nickel) in three scenarios during macroeconomic crises: A machine learning-based approach
Seyed Mehdi Haji Mirarab1 Elahe Meigoonpoori2 Azam Naderi3 Seyed Sasan Golchobian4 Seyed Mohammadreza Nojaba5 Seyed Ehtesham Seyedali Rooteh6
1) Professional Doctorate(DBA) in Business
2) PhD in Entrepreneurship
3) Master of Business Administration
4) Master of Science in Information Technology Management
5) Master of Business Administration
6) PhD student in economics
IOI Code
:
AAGK-ABBCDA
Publication :
4th International Conference on Researches in Accounting, Economics, Management & Humanities(meaconf.com/4th)
Abstract :
The purpose of this study is to examine the financial performance of Chrome Nickel Company in the face of macroeconomic and political crises during the period 1394 to the third quarter of 1404 and to provide a medium-term forecast for the year 1405. The research data includes performance indicators such as earnings per share, return on assets, return on equity, net profit margin, and operating cash flow as dependent variables. Within the methodological framework, a combination of classical econometric models and machine learning algorithms including Profit, Arimax, Random Forest, and XG Boost was used, and structural shocks such as the intensification of sanctions, economic unrest, the Corona pandemic, geopolitical tensions, and policy uncertainties were included in the model training process. The findings show that the financial performance of companies at the peak, until the shocks of 1404, will face a decline of about 15% in the pessimistic scenario and a decline of 7% in the base scenario or stability of the situation. In the optimistic scenario, a 1% increase in financial performance was observed, which will occur if international pressures and the shadow of war are largely eliminated. The results of the validity assessment of the models indicate the superiority of the XG Boost model with a higher coefficient of determination and lower prediction error compared to other methods. Overall, the results emphasize that the use of machine learning models can provide a more accurate understanding of the nonlinear behavior of firms financial performance in unstable economies and provide a suitable tool for investors and policymakers to make decisions.
Keywords : financial performance machine learning macroeconomic crises financial forecasting