Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Koffi, Cedric H. A., Djeundje, Viani Biatat, Pamen, Olivier Menoukeu
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2410.13100
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913983612583936
author Koffi, Cedric H. A.
Djeundje, Viani Biatat
Pamen, Olivier Menoukeu
author_facet Koffi, Cedric H. A.
Djeundje, Viani Biatat
Pamen, Olivier Menoukeu
contents We develop and evaluate a family of discrete-time logit-link (LLink) models (including fixed-effects and frailty extensions) to capture latent heterogeneity in repayment behaviour and quantify the effects of socio-temporal factors in microfinance. Our findings highlight the importance of unobserved borrower risk, revealing that simple random intercept structures are sufficient to model latent heterogeneity in this context. Additionally, socio-temporal variables--such as festive seasons and long school breaks--consistently associate with delinquency transitions, offering key insights into repayment dynamics. While LLink models provide clear interpretability, tree-based methods outperform them in predictive accuracy, making them suitable for multistate classification tasks. Building on this, we propose an optimised classification strategy based on the Matthews Correlation Coefficient to enhance next-state prediction. Overall, our results highlight the benefit of combining interpretable risk modeling with advanced machine learning to support robust, data-driven decision-making in microfinance operations.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13100
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quantifying socio-temporal effects of loan delinquency drivers in microfinance
Koffi, Cedric H. A.
Djeundje, Viani Biatat
Pamen, Olivier Menoukeu
Risk Management
We develop and evaluate a family of discrete-time logit-link (LLink) models (including fixed-effects and frailty extensions) to capture latent heterogeneity in repayment behaviour and quantify the effects of socio-temporal factors in microfinance. Our findings highlight the importance of unobserved borrower risk, revealing that simple random intercept structures are sufficient to model latent heterogeneity in this context. Additionally, socio-temporal variables--such as festive seasons and long school breaks--consistently associate with delinquency transitions, offering key insights into repayment dynamics. While LLink models provide clear interpretability, tree-based methods outperform them in predictive accuracy, making them suitable for multistate classification tasks. Building on this, we propose an optimised classification strategy based on the Matthews Correlation Coefficient to enhance next-state prediction. Overall, our results highlight the benefit of combining interpretable risk modeling with advanced machine learning to support robust, data-driven decision-making in microfinance operations.
title Quantifying socio-temporal effects of loan delinquency drivers in microfinance
topic Risk Management
url https://arxiv.org/abs/2410.13100