On building early-warning systems for preventing the deterioration of financial institutions’ performance


This paper assesses the financial performance of Romania’s non-banking financial institutions (NFIs) using a neural network training algorithm proposed by Kohonen, namely the Self-Organizing Maps algorithm. The algorithm takes the financial dataset and positiones each observation into a self-organizing map (a two-dimensional map) which can be latter used to visualize the trajectories of an individual NFI and explain it based on different performance dimensions, such as capital adequacy, assets’ quality and profitability. Further, we use the map as an early-warning system that would accurately forecast the NFIs future performance (whether they would stay or be eliminated from the NFI’s Special Register three quarters into the future). The results are promising: the model is able to correctly predict NFIs’ performance movements. Finally, we compared the results of our SOM-based model with those obtained by applying a multivariate logit-based model. The SOM model performed worse in discriminating the NFIs’ performance: the performance classes were not clearly defined and the model lacked the interpretability of the results. In the contrary, the multivariate logit coefficients have nice interpretability and an individual default probability estimate is obtained for each new observation. However, we can benefit from the results of both techniques: the visualization capabilities of the SOM model and the interpretability of multivariate logit-based model.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • Borio, C., & Lowe, P. (2002). Assessing the risk of banking crises. BIS Quarterly Review, No. December, 43-54.

  • Bussière, M., & Fratzscher, M. (2002). Towards a newly warning system of financial crisis. European Central Bank Working Paper Series, Working Paper No. 145.

  • Candelon, B., Dumitrescu, E., & Hurlin, C. (2009). How to evaluate an early-warning system: Toward a unified statistical framework for assessing financial crises forecasting methods. Maastricht University (RM/10/046).

  • Cerna, S., Donath, L., Seulean, V., Herbei, M., Bărglăzan, D., Albulescu, C., & Boldea, B. (2008). Financial Stability. Timişoara: West University Publishing House.

  • Costea, A. (2005). Computational Intelligence Methods for Quantitative Data Mining. TUCS PhD dissertation No. 67, Åbo Akademi University, Turku, Finland.

  • Costea, A. (2006). The Analysis of the Telecommunications Sector by the Means of Data Mining Techniques. Journal of Applied Quantitative Methods (JAQM), 1(2), 144-150.

  • Costea, A. (2013). Performance benchmarking of non-banking financial institutions by means of Self-Organising Map algorithm. East-West Journal of Economics and Business, XVI(1), 37-58.

  • Costea, A., & Bleotu, V. (2012). A new fuzzy clustering algorithm for evaluating the performance of non-banking financial institutions in Romania. Economic Computation and Economic Cybernetics Studies and Research, 46(4), 179-199.

  • Costea, A., & Eklund, T. (2003). A Two-Level Approach to Making Class Predictions. In RH. Sprague Jr. (ed.), Proceedings of 36th Annual Hawaii International Conference on System Sciences (HICSS 2003) (9 pages). IEEE Computer Society, Hawaii, USA, January 6-9, 2003, Track: Decision Technologies for Management, Minitrack: Intelligent Systems and Soft Computing, ISBN: 0-7695-1874-5.

  • Davis, E.P., & Karim, D. (2008). Comparing Early Warning Systems for Banking Crises. Journal of Financial Stability, 4(2), 89-120.

  • Demirgüç-Kunt, A., & Detragiache, E. (1999). Monitoring banking sector fragility: A multivariate approach with an application to the 1996-97 crisis. Working Paper of the International Monetary Fund, No. 147.

  • Drehmann, M., & Juselius, M. (2013). Evaluating early warning indicators of banking crises: Satisfying policy requirements. BIS Working Papers, No. 421.

  • Hardy, D.C., & Pazarbașioğlu, C. (1998). Leading Indicators of Banking Crises: Was Asia different? Working Paper of the International Monetary Fund, No. 91.

  • Janes, H., Longton, G., & Pepe, M. (2009). Accommodating covariates in ROC analysis. Stata Journal, 9.

  • Kaminsky, G.L., & Reinhart, C.M. (1999). The twin crises: the causes of banking and balance-of-payments problems. American Economic Review, 89(3), 473-500.

  • Kohonen, T. (1997). Self-Organising Maps (2nd ed.). Heidelberg: Springer-Verlag.

  • Kohonen, T., Hynninen, J., Kangas, J., & Laaksonen, J. (1996). SOM_PAK: The Self-Organising Map Program Package. Helsinki University of Technology, Report A31, Otaniemi.

  • Moinescu, B., & Costea, A. (2014). Towards an early-warning system of distressed non-banking financial institutions. Economic Computation and Economic Cybernetics Studies and Research, 48(2), 75-90.

  • Pepe, M., Janes, H., & Longton, G. (2009). Estimation and comparison of receiver operating characteristic curves. Stata Journal, 9.


Journal + Issues