Title: Corporate failure prediction model for European SMEs

Authors: Sónia Silva

Addresses: NIPE (Centre for Research in Economics and Management), School of Economics and Management, University of Minho, Campus de Gualtar, 4710-057 Braga, Portugal

Abstract: We propose a corporate failure prediction model that provides forecasting ability up to three years before the failure event. We use a longitudinal panel data over 2012-2019 retrieved from Orbis Europe formed of EU-based SMEs, analysed under different methodologies such as multiple discriminant analysis and logistic analysis. Our final insolvency prediction model includes EU-based SMEs failure determinants across all industries: cash ratio, contribution (per interest paid) ratio, solvency ratio, short-term financing, leverage, debt-assets ratio, and return on assets. Our model correctly predicts more than 70% of the observations three years before the event. The overall accuracy of the proposed model is about 82%. Our model results from a trade-off between interpretability and accuracy, targeting the interest of managers, analysts, investors, and remaining stakeholders allowing easy application and interpretation of the outcome.

Keywords: financial distress; prediction model; multiple discriminant analysis; SMEs; European Union; logit model; bankruptcy; insolvency; financial ratios; corporate failure.

DOI: 10.1504/GBER.2026.154029

Global Business and Economics Review, 2026 Vol.34 No.4, pp.395 - 419

Received: 20 May 2024
Accepted: 13 Sep 2024
Published online: 10 Jun 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article