<abstract xmlns="http://www.w3.org/1999/xhtml"><p>In this paper we evaluate comparatively the performance of non-banking financial institutions in Romania by the means of unsupervised neural networks in terms of Kohonen’ Self-Organizing Maps algorithm. We create a benchmarking model in the form of a two-dimensional map (a self-organizing map) that can be used to assess visually the performance of non-banking financial institutions based on different performance dimensions, such as capital adequacy, assets’ quality and profitability. We use the following indicators: Equity ratio (Leverage) for the capital adequacy dimension, Loans granted to clients (net value) / total assets (net value) for the assets’ quality dimension and Return on assets (ROA) for the profitability dimension. We have excluded from our analysis the other three dimensions used in evaluating the performance of banks, due to lack of data (for the two qualitative dimensions: quality of ownership and management) and irrelevance with the NFIs’ sector (liquidity). The proposed model is based on the Self-Organising Map algorithm which creates a two-dimensional map (e.g. 6x4 = 24 neurons) from p-dimensional input data. The data were collected for eleven non-banking financial institutions for four years 2007-2010, in total 44 observations. Using the visualization capabilities of the Self-Organising Map model and the trajectories we show the movements of the three non-banking financial institutions with the worst performance: the largest underperformer denoted with X, the second largest underperformer denoted with Y and the third largest underperformer denoted with Z between 2007 and 2010.</p></abstract>

In this paper we evaluate comparatively the performance of non-banking financial institutions in Romania by the means of unsupervised neural networks in terms of Kohonen’ Self-Organizing Maps algorithm. We create a benchmarking model in the form of a two-dimensional map (a self-organizing map) that can be used to assess visually the performance of non-banking financial institutions based on different performance dimensions, such as capital adequacy, assets’ quality and profitability. We use the following indicators: Equity ratio (Leverage) for the capital adequacy dimension, Loans granted to clients (net value) / total assets (net value) for the assets’ quality dimension and Return on assets (ROA) for the profitability dimension. We have excluded from our analysis the other three dimensions used in evaluating the performance of banks, due to lack of data (for the two qualitative dimensions: quality of ownership and management) and irrelevance with the NFIs’ sector (liquidity). The proposed model is based on the Self-Organising Map algorithm which creates a two-dimensional map (e.g. 6x4 = 24 neurons) from p-dimensional input data. The data were collected for eleven non-banking financial institutions for four years 2007-2010, in total 44 observations. Using the visualization capabilities of the Self-Organising Map model and the trajectories we show the movements of the three non-banking financial institutions with the worst performance: the largest underperformer denoted with X, the second largest underperformer denoted with Y and the third largest underperformer denoted with Z between 2007 and 2010.

Classifying non-banking financial institutions based on their financial performance

Proceedings of the International Conference on Applied Statistics

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

In this paper we evaluate comparatively the performance of non-banking financial institutions in Romania by the means of unsupervised neural networks in terms...

Classifying non-banking financial institutions based on their financial performance

Data publikacji: 13 lut 2020

Zakres stron: 185 - 193

DOI: https://doi.org/10.2478/icas-2019-0016

Słowa kluczowe
non-banking financial institutions, self-organising maps, performance evaluation, benchmarking, financial ratios

© 2019 Adrian Costea, published by Sciendo

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

Classifying non-banking financial institutions based on their financial performance

Data publikacji: 13 lut 2020

Zakres stron: 185 - 193

DOI: https://doi.org/10.2478/icas-2019-0016

Słowa kluczowenon-banking financial institutions, self-organising maps, performance evaluation, benchmarking, financial ratios

© 2019 Adrian Costea, published by Sciendo

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

Słowa kluczowe
non-banking financial institutions, self-organising maps, performance evaluation, benchmarking, financial ratios