Using Decision Trees to Predict Insolvency in Spanish SMEs: Is Early Warning Possible?

Andrés Navarro-Galera (), Juan Lara-Rubio, Pavel Novoa-Hernández () and Carlos A. Cruz Corona ()
Additional contact information
Andrés Navarro-Galera: University of Granada
Juan Lara-Rubio: University of Granada
Pavel Novoa-Hernández: University of Granada
Carlos A. Cruz Corona: University of Granada

Computational Economics, 2025, vol. 65, issue 1, No 4, 116 pages

Abstract: Abstract In today’s economic landscape, with its increasingly brief economic cycles and ever-changing market conditions, forecasting has become more critical than ever. In the specific case of small and medium-sized enterprises (SMEs), a crucial aspect is to anticipate the state of bankruptcy due to the low life expectancy of this type of company. A requirement that has been recommended by several international organizations such as the European Union, especially because SMEs contribute significantly to job creation and added value and to overcoming the effects of economic crises. Despite the progress in this field, there are economies that have been little or poorly addressed by the literature. This is the case for Spain, an economy where SMEs account for a significant share of its business landscape. To close this gap, this paper addressed the problem of predicting the insolvency of Spanish SMEs from a Machine Learning perspective. Leveraging a dataset encompassing financial and non-financial data from 58,267 Spanish SMEs spanning the period 2009–2020, we adjusted several decision tree models to address two scenarios of practical value in the Spanish context. Additionally, we conducted a thorough analysis of the most influential predictors of insolvency from a financial perspective. To empower Spanish SMEs, we provided them with a free software tool implementing the best models for the considered scenarios. The tool is intended to serve as an additional means to proactively and early assess solvency status.

Keywords: Insolvency prediction; SME; Decision trees; Binary classification (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10614-024-10586-5 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:kap:compec:v:65:y:2025:i:1:d:10.1007_s10614-024-10586-5

Ordering information: This journal article can be ordered from
http://www.springer. ... ry/journal/10614/PS2

DOI: 10.1007/s10614-024-10586-5

Access Statistics for this article

Computational Economics is currently edited by Hans Amman

More articles in Computational Economics from Springer, Society for Computational Economics Contact information at EDIRC.
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().