Academic

Selection of over time stability ratios using machine learning techniques

According to the data provided by Coface platform, there are almost 3.8 million registered companies in the Visegrad Group (V4), with a significantly increased number of bankruptcies over the last years. Therefore, the main aim of this paper is to identify stable key indicators that determine the financial condition of these companies, which is of crucial importance for stakeholders and investors. To address this topic, we rely on the original dataset consisting of 145,638 company-years from the V4 countries, covering six main sectors during the period of 2018-2021. We calculate 78 financial and non-financial ratios, and we build a robust framework for the identification of the most important ones. Our framework relies on explainable machine learning techniques followed by cross-country and cross-sectional comparisons of the indicators. The results reveal that most of the non-financial indicators included in the analysis are important in assessing the financial condition of companies.

S
Sebastian Klaudiusz Tomczak · · 1 min read · 17 views

According to the data provided by Coface platform, there are almost 3.8 million registered companies in the Visegrad Group (V4), with a significantly increased number of bankruptcies over the last years. Therefore, the main aim of this paper is to identify stable key indicators that determine the financial condition of these companies, which is of crucial importance for stakeholders and investors. To address this topic, we rely on the original dataset consisting of 145,638 company-years from the V4 countries, covering six main sectors during the period of 2018-2021. We calculate 78 financial and non-financial ratios, and we build a robust framework for the identification of the most important ones. Our framework relies on explainable machine learning techniques followed by cross-country and cross-sectional comparisons of the indicators. The results reveal that most of the non-financial indicators included in the analysis are important in assessing the financial condition of companies.

Executive Summary

The article titled 'Selection of over time stability ratios using machine learning techniques' investigates the financial stability of companies within the Visegrad Group (V4) using a comprehensive dataset of 145,638 company-years from 2018 to 2021. The study calculates 78 financial and non-financial ratios to identify key indicators of financial health. Employing explainable machine learning techniques, the research reveals that non-financial indicators are particularly significant in assessing the financial condition of companies. The findings have implications for stakeholders, investors, and policymakers in understanding and mitigating financial risks in the V4 region.

Key Points

  • ▸ The study uses a large dataset of 145,638 company-years from V4 countries.
  • ▸ It calculates 78 financial and non-financial ratios to identify key indicators.
  • ▸ Explainable machine learning techniques are employed to determine the most important indicators.
  • ▸ Non-financial indicators are found to be crucial in assessing financial health.
  • ▸ The findings have significant implications for stakeholders and policymakers.

Merits

Comprehensive Dataset

The study utilizes a large and diverse dataset, enhancing the robustness and generalizability of the findings.

Advanced Methodology

The use of explainable machine learning techniques provides a transparent and interpretable framework for identifying key indicators.

Cross-Country and Cross-Sectional Analysis

The study's comparative approach allows for a nuanced understanding of financial stability across different sectors and countries.

Demerits

Temporal Limitations

The dataset covers only a four-year period, which may limit the long-term applicability of the findings.

Geographical Focus

The study is limited to the V4 countries, which may not be representative of other regions or economic contexts.

Data Quality and Availability

The reliance on data from the Coface platform may introduce biases or limitations in the data quality and coverage.

Expert Commentary

The study presents a rigorous and well-structured approach to identifying key indicators of financial stability using machine learning techniques. The comprehensive dataset and advanced methodology enhance the credibility of the findings. However, the temporal and geographical limitations of the study warrant caution in generalizing the results. The emphasis on non-financial indicators is particularly noteworthy, as it challenges traditional financial analysis frameworks. The study's findings have significant implications for investors, stakeholders, and policymakers, providing a foundation for further research and practical applications. The use of explainable machine learning techniques is commendable, as it ensures transparency and interpretability, which are crucial for decision-making in financial contexts.

Recommendations

  • ✓ Future research should extend the temporal scope of the dataset to include a longer period, enhancing the long-term applicability of the findings.
  • ✓ The study's methodology could be applied to other regions or economic contexts to validate and expand the findings.

Sources

Related Articles