Scholarlink

<p>The objective of this study is to anticipate the repayment behaviors of financially vulnerable debtors in Korea using a prediction model employing a stacking algorithm. To accomplish this goal, this study is conducted on 1,171,204 debtors with delinquent loans acquired by KAMCO since 2018. Following this analysis, the meta-model successfully predicted 87.7% of vulnerable debtors’ repayment decisions, thus validating its efficacy in discerning debtors with high repayment potential. In addition, it is confirmed that a stacking algorithm can be utilized to construct a prediction model that can be universally applied across a wider range, resulting in a substantial increase in accuracy. This study is significant as it empirically predicts the repayment likelihood of vulnerable debtors in Korea through the utilization of data regarding large-scale non-performing loans. Moreover, the findings of this analysis suggest that financial institutions can enhance their proficiency in loan management by screening and overseeing debtors based on their repayment potential.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Predicting the Repayment Decisions of Korean Vulnerable Debtors: Evidence from an Empirical Study Utilizing a Stacking Algorithm

  • 期刊论文

  • 发表日期：

    2025年2月12日

查看全文
  • Youngwoo Jeong

摘要

The objective of this study is to anticipate the repayment behaviors of financially vulnerable debtors in Korea using a prediction model employing a stacking algorithm. To accomplish this goal, this study is conducted on 1,171,204 debtors with delinquent loans acquired by KAMCO since 2018. Following this analysis, the meta-model successfully predicted 87.7% of vulnerable debtors’ repayment decisions, thus validating its efficacy in discerning debtors with high repayment potential. In addition, it is confirmed that a stacking algorithm can be utilized to construct a prediction model that can be universally applied across a wider range, resulting in a substantial increase in accuracy. This study is significant as it empirically predicts the repayment likelihood of vulnerable debtors in Korea through the utilization of data regarding large-scale non-performing loans. Moreover, the findings of this analysis suggest that financial institutions can enhance their proficiency in loan management by screening and overseeing debtors based on their repayment potential.