School of Business

Using Machine Learning Algorithms to Improve Fiscal Distress Prediction Models: The Case of U.S. Local Governments

Document Type

Article

Abstract

This study aims to improve the prediction of fiscal distress in local governments (LGs) using machine learning (ML) methods. We apply six ML algorithms, including Logistic Regression, XGBClassifier, RUSBoost, C4.5 Decision Tree, Exactly Balanced Bagging, and Roughly Balanced Bagging, which are combined with and without two undersampling methods—Majority Sampling and Optimal Ratio Sampling—to predict fiscal distress of LGs. Analyzing financial and socioeconomic indicators from LGs across 49 U.S. states from 2015 to 2017, we find that regardless of undersampling strategy, the Exactly Balanced Bagging Classifier generally outperforms other ML algorithms including Logistic Regression: its F1-scores range from 53.11 percent to 55.33 percent, significantly higher than 27 percent to 58 percent of Logistic Regression. Furthermore, Optimal Ratio Sampling offers the most significant benefit to Logistic Regression. These findings offer valuable insights into the analysis and prediction of municipal fiscal distress, particularly within the context of imbalanced datasets. © 2025, American Accounting Association. All rights reserved.

Publication Title

Journal of Information Systems

Publication Date

Fall 2025

Volume

39

Issue

3

First Page

131

Last Page

155

ISSN

0888-7985

DOI

10.2308/ISYS-2023-049

Keywords

Chapter 9, fiscal distress, local governments (LGs), machine learning (ML) classifier, municipal bankruptcy, technically insolvent

Link to Full Text

Share

COinS