The financial crisis affecting local governments poses a significant threat to the stability of public finance. Current procedures, based on ex post indicators and rigid thresholds, have proven largely ineffective in preventing situations of fiscal imbalance. This study introduces a predictive model grounded in cash flow analysis and applies the Random Forest algorithm to an experimental dataset covering 200 municipalities in Campania, Calabria, and Sicily over the 2022–2024 period. The analysis confirms the robustness of the model and highlights the potential of machine learning as an early warning tool. The results underscore the importance of integrating predictive technologies into local governments’ financial monitoring and governance systems.
Tecnologie digitali e prevenzione del dissesto negli enti locali: : un modello predittivo basato sull’analisi dei flussi di cassa
D'Alessio, Antonio
;D'Amore, Gabriella;Scaletti, Alessandro
2026-01-01
Abstract
The financial crisis affecting local governments poses a significant threat to the stability of public finance. Current procedures, based on ex post indicators and rigid thresholds, have proven largely ineffective in preventing situations of fiscal imbalance. This study introduces a predictive model grounded in cash flow analysis and applies the Random Forest algorithm to an experimental dataset covering 200 municipalities in Campania, Calabria, and Sicily over the 2022–2024 period. The analysis confirms the robustness of the model and highlights the potential of machine learning as an early warning tool. The results underscore the importance of integrating predictive technologies into local governments’ financial monitoring and governance systems.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
