| Abstrakt: |
This study aims to analyze the financial condition of the accounting sector in Poland. The population consisted of the financial statements of companies from the period 2015-2023. The final sample included 46436 data specimens from 11022 companies during nine consecutive years. The results of the descriptive analysis confirm that the firms from the accounting sector in Poland are in good financial condition despite the complexities posed by the ongoing COVID-19 pandemic and the Russia-Ukraine war. In the predictive analytics, the K-nearest neighbor classifier was employed to predict the occurrence of profit in companies from the accounting sector in Poland. The independent variables in the study were the financial ratios: log of revenue, log of assets, and age of the company. The model was built using the programming language Python and its libraries, including pandas, NumPy, matplotlib, and scikit-learn. The developed model had an accuracy of 78%. The results of this study showed that among the analyzed variables, company size measured by the log of revenue is the most essential feature in predicting profit. This study makes four main contributions. First, it presents the financial health analysis of Poland's accounting sector and extends the literature on building models using machine learning algorithms. The developed model is based on real financial data. Second, it provides a methodology for designing and implementing the ML approach for scientists. Third, these findings are pivotal considerations for investors evaluating the financial condition of the accounting sector and potential future growth. Finally, it can be helpful for managers to make better data-driven decisions by identifying trends in the financial parameters and predicting future performance using an ML model. The findings must be interpreted in light of certain limitations; the main concern is that this study focused only on accounting firms from Poland. [ABSTRACT FROM AUTHOR] |
