EconPapers    
Economics at your fingertips  
 

Machine learning methods for the prediction of municipal financial distress: evidence from Italy

Matteo Bergamaschi (), Michele Cascarano, Anna Laura Mancini (), Francesco Rinaldi () and Giacomo Ziglio ()
Additional contact information
Matteo Bergamaschi: Universita' di Padova
Anna Laura Mancini: Bank of Italy
Francesco Rinaldi: Universita' di Padova
Giacomo Ziglio: Bank of Italy

No 1078, Questioni di Economia e Finanza (Occasional Papers) from Bank of Italy, Economic Research and International Relations Area

Abstract: This paper develops a data-driven framework for predicting severe financial distress in Italian municipalities. Using a balanced panel of 7,778 municipalities over 2009-23, it makes four contributions. First, it introduces daily treasury-advance data from SIOPE as a high-frequency indicator of liquidity stress. Second, it compares predictive exercises based on comprehensive financial statements, provisional budget forecasts and indicators developed by the Italian Court of Auditors. Third, it evaluates several machine learning (ML) methods against traditional econometric benchmarks. Fourth, it applies interpretability techniques to identify the factors underlying model predictions and support supervisory assessment. The results indicate that advanced ML models provide more accurate predictions than the current regulatory system for the early identification of financial distress. Predictive performance is generally stronger over two- and three-year horizons than for one-year-ahead forecasts. While daily treasury-advance indicators have limited standalone predictive power, they provide timely information on liquidity conditions and may strengthen early-warning systems when combined with budget forecasts or accounting data.

Keywords: financial distress; Italian local government; data-driven approach; daily treasury advances; interpretability (search for similar items in EconPapers)
JEL-codes: C45 C53 G33 H72 H74 (search for similar items in EconPapers)
Date: 2026-11
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.bancaditalia.it/pubblicazioni/qef/2026-1078/QEF_1078_26.pdf (application/pdf)

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:bdi:opques:qef_1078_26

Access Statistics for this paper

More papers in Questioni di Economia e Finanza (Occasional Papers) from Bank of Italy, Economic Research and International Relations Area Contact information at EDIRC.
Bibliographic data for series maintained by ().

 
Page updated 2026-11-17
Handle: RePEc:bdi:opques:qef_1078_26