The effects of company characteristics on financial reporting quality – the application of the machine learning technique
The effects of company characteristics on financial reporting quality – the application of the machine learning technique

Summary/Abstract: Purpose: The paper aims to determine the level of financial reporting quality (FRQ) in listed companies in Croatia, as an example of a macro-based accounting system with an underdeveloped capital market, and identify company characteristics that affect it. The paper systematizes the existing key knowledge of FRQ. Furthermore, it critically analyses the principles and direction of influence of various qualitative and quantitative as well as financial and non-financial characteristics of a company.Methodology: The empirical analyses involve joint testing of the machine learning technique (MLT) and the economic hypotheses. M5 algorithm is applied to identify the factors that influence the quality of voluntary reporting as well as the direction and intensity of their influence.Results: The results show that profitability, stock market listing duration (in years), and company size positively affect the level and extent of FRQ through voluntary disclosure of information in the annual financial reports of Croatian listed companies. In addition, differences in FRQ between different areas of economic activity and depending on the type of auditor were found.Conclusion: Croatian companies should adopt good reporting practices to meet the requirements of the global market and thus contribute to the improvement of the overall transparency system. The same is expected from the relevant regulatory authorities who should encourage full disclosure. The paper provides several scientific contributions: first, the spatial dimension of the research; second, the comprehensive literature review; and third, the MLT application in the research on FRQ. An important practical implication of these findings is that they will help financial statement users in the economic decision-making process.

• Details
• Contents