Purpose: This study examines the relationship between intellectual capital (IC) and the likelihood of bankruptcy among Italian unlisted firms and assesses whether IC-based measures improve bankruptcy prediction accuracy. Methodology: A random-effects logistic regression with lagged covariates, year and industry fixed effects, and firm-level clustered errors is employed. Predictive accuracy is evaluated using ROC curves, the Area Under the Curve (AUC), and the DeLong test. Findings: IC is negatively and significantly related to bankruptcy likelihood, indicating that firms managing IC efficiently are less prone to financial failure. Models including IC show higher predictive accuracy than those based only on financial indicators. Managerial implications: The results demonstrate that IC enhances financial resilience among unlisted firms. Managers should develop and monitor IC to prevent bankruptcy, while policymakers are encouraged to promote IC disclosure to improve transparency and credit risk assessment. Research limitations: The study focuses on Italian unlisted firms and uses the VAIC model within a logistic regression framework, which may not capture all IC dimensions or non-linear effects. Originality: By exploring IC’s role in bankruptcy risk among unlisted firms, this study fills a gap in the literature and provides new evidence on how IC improves the predictive performance of bankruptcy models.
The Predictive Role of Intellectual Capital in Corporate Bankruptcy: Evidence from Unlisted Firms / Baccarini, L., D'Ezio, M., Poli, S.. - ELETTRONICO. - XLI:(2026), pp. 242-260. (XLI CONVEGNO NAZIONALE AIDEA LE INTELLIGENZE AZIENDALI PER LA COMPETITIVITÀ SOSTENIBILE E IL BENE COMUNE Milano 22-23 gennaio 2026).
The Predictive Role of Intellectual Capital in Corporate Bankruptcy: Evidence from Unlisted Firms
Baccarini Luca
Primo
;D'Ezio MarcoSecondo
;Poli SimoneUltimo
2026-01-01
Abstract
Purpose: This study examines the relationship between intellectual capital (IC) and the likelihood of bankruptcy among Italian unlisted firms and assesses whether IC-based measures improve bankruptcy prediction accuracy. Methodology: A random-effects logistic regression with lagged covariates, year and industry fixed effects, and firm-level clustered errors is employed. Predictive accuracy is evaluated using ROC curves, the Area Under the Curve (AUC), and the DeLong test. Findings: IC is negatively and significantly related to bankruptcy likelihood, indicating that firms managing IC efficiently are less prone to financial failure. Models including IC show higher predictive accuracy than those based only on financial indicators. Managerial implications: The results demonstrate that IC enhances financial resilience among unlisted firms. Managers should develop and monitor IC to prevent bankruptcy, while policymakers are encouraged to promote IC disclosure to improve transparency and credit risk assessment. Research limitations: The study focuses on Italian unlisted firms and uses the VAIC model within a logistic regression framework, which may not capture all IC dimensions or non-linear effects. Originality: By exploring IC’s role in bankruptcy risk among unlisted firms, this study fills a gap in the literature and provides new evidence on how IC improves the predictive performance of bankruptcy models.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


