Research

 Limited liability companies can   experience serious financial problems due to bad economy or unsuccessful business transactions. This can in the worst case results in the company bankruptcy. Having indicator that will warn managers in advance may be very useful since company may attempt to remedy its financial situation and take corrective actions. In reality only fraction of all companies face bankruptcy herefore we approach this issue as an classification of imbalanced dataset. We work with financial data of thousands of limited liability companies and try to predict the bankruptcy several  years before it actually happens.

Try our app to predict imminent bankruptcy of the company. The app is based on our previous research and it is recommended for  small and medium limited liability companies.

We collected the dataset of financial ratios of limited liability companies that can be used to benchmark and validate methods for imbalanced learning and bankruptcy prediction. The detailed description can be found in our Data in Brief paper.

Related publications:

Zoričák, M,  Gnip, P.,  Drotár, P., Gazda, V. (2019). Small- and medium-enterprises bankruptcy dataset. Data in Brief. vol. 25. https://doi.org/10.1016/j.dib.2019.104360

Zoričák, M,  Gnip, P.,  Drotár, P., Gazda, V. (2019). Bankruptcy prediction for small- and medium-sized companies using severely imbalanced datasets. Economic Modelling. ISSN 0264-9993,
https://doi.org/10.1016/j.econmod.2019.04.003.

Drotár P., Gnip, P., Zoričák, M.,Gazda, V. (2018).  Single-Class Bankruptcy Prediction Based on the Data from Annual Reports. In: Intelligent data engineering and automated learning : Part 1. Springer Nature s. 343-353 [online]. Madrid. Španielsko. ISBN 978-3-030-03492-4

Gnip, P., Zoričák, M., Drotár P. (2017). Predikcia úpadku spoločností s ručením obmedzeným využitím metód pre rozpoznanie odľahlých bodov.In: Dáta a znalosti 2017, Plzeň, CZE.

Drotár P., Zoričák, M., Gnip, P. (2018). Predikcia úpadku s.r.o. využitím metód pre rozpoznanie odľahlých bodov na nevyvážených dátach. In: Dáta a znalosti 2018, Brno, CZE.