<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>The main purpose of this study is to investigate the best predictor of firm performance among different proxies. A sample of 287 Czech firms was taken from automobile, construction, and manufacturing sectors. Panel data of the firms was acquired from the Albertina database for the time period from 2016 to 2020. Three different proxies of firm performance, return of assets (RoA), return of equity (RoE), and return of capital employed (RoCE) were used as dependent variables. Including three proxies of firm’s performance, 16 financial ratios were measured based on the previous literature. A machine learning-based decision tree algorithm, Chi-squared Automatic Interaction Detector (CHAID), was deployed to gauge each proxy’s efficacy and examine the best proxy of the firm performance. A partitioning rule of 70:30 was maintained, which implied that 70% of the dataset was used for training and the remaining 30% for testing. The results revealed that return on assets (RoA) was detected to be a robust proxy to predict financial performance among the targeted indicators. The results and the methodology will be useful for policy-makers, stakeholders, academics and managers to take strategic business decisions and forecast financial performance.</p>
</abstract>

The main purpose of this study is to investigate the best predictor of firm performance among different proxies. A sample of 287 Czech firms was taken from automobile, construction, and manufacturing sectors. Panel data of the firms was acquired from the Albertina database for the time period from 2016 to 2020. Three different proxies of firm performance, return of assets (RoA), return of equity (RoE), and return of capital employed (RoCE) were used as dependent variables. Including three proxies of firm’s performance, 16 financial ratios were measured based on the previous literature. A machine learning-based decision tree algorithm, Chi-squared Automatic Interaction Detector (CHAID), was deployed to gauge each proxy’s efficacy and examine the best proxy of the firm performance. A partitioning rule of 70:30 was maintained, which implied that 70% of the dataset was used for training and the remaining 30% for testing. The results revealed that return on assets (RoA) was detected to be a robust proxy to predict financial performance among the targeted indicators. The results and the methodology will be useful for policy-makers, stakeholders, academics and managers to take strategic business decisions and forecast financial performance.

Best proxy to determine firm performance using financial ratios: A CHAID approach

Review of Economic Perspectives

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

The main purpose of this study is to investigate the best predictor of firm performance among different proxies. A sample of 287 Czech firms was taken from...

Best proxy to determine firm performance using financial ratios: A CHAID approach

Data publikacji: 27 wrz 2022

Zakres stron: 219 - 239

Otrzymano: 24 mar 2022

Przyjęty: 26 lip 2022

DOI: https://doi.org/10.2478/revecp-2022-0010

Słowa kluczowe
Czech firms, Decision tree, financial ratios, firm performance, return on assets

© 2022 Muhammad Yousaf et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Best proxy to determine firm performance using financial ratios: A CHAID approach

Data publikacji: 27 wrz 2022

Zakres stron: 219 - 239

Otrzymano: 24 mar 2022

Przyjęty: 26 lip 2022

DOI: https://doi.org/10.2478/revecp-2022-0010

Słowa kluczoweCzech firms, Decision tree, financial ratios, firm performance, return on assets

© 2022 Muhammad Yousaf et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Słowa kluczowe
Czech firms, Decision tree, financial ratios, firm performance, return on assets