Title: Analysis of the debt status of households in poor areas based on economic capital using two-class boosted decision tree

Authors: Pita Jarupunphol; Wipawan Buathong; Suthasinee Kuptabut

Addresses: Department of Digital Technology, Phuket Rajabhat University, Phuket, Thailand ' Department of Digital Technology, Phuket Rajabhat University, Phuket, Thailand ' Department of Computer, Sakon Nakhon Rajabhat University, Sakon Nakhon, Thailand

Abstract: This study examines household debt determinants in Kut Bak district, Thailand, using a two-class boosted decision tree (TBDT) model to analyse 301 households across 30 financial, asset, and socio-economic variables. Compared with logistic regression, decision tree, random forest, and XGBoost, the model demonstrates superior performance, achieving an accuracy of 0.922, precision of 0.975, recall of 0.867, F1-score of 0.918, and AUC of 0.948. Key findings reveal that limited savings, minimal state assistance, and low ownership of productive assets significantly increase debt likelihood. Specific thresholds, such as savings below 4,500 units and cash reserves of 50 units or less, are strongly associated with indebtedness. The study highlights the model's effectiveness in predicting debt status and provides actionable insights for policymakers and organisations to enhance financial stability in rural communities. These results contribute to understanding socio-economic factors driving household debt in disadvantaged areas.

Keywords: data mining; household debt; machine learning; socio-economic factors; two-class boosted decision tree; TBDT.

DOI: 10.1504/IJDMMM.2026.154488

International Journal of Data Mining, Modelling and Management, 2026 Vol.18 No.2, pp.158 - 179

Received: 23 Feb 2024
Accepted: 29 Jan 2025
Published online: 30 Jun 2026 *

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