Machine learning models for predicting mortgage payment difficulties in Peru
The objective of this study was to analyze which machine learning models best predict mortgage payment difficulties in Peru.A quantitative method was used with longitudinal data from 2018 to 2022 from the National Household Survey (ENAHO), where a total of 5,716 households with mortgage loans were e...
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Artículo |
| Lenguaje: | inglés |
| Publicado: |
2025
|
| Acceso en línea: | Descargar el archivo Enlace permanente (DOI o Handle) Enlace permanente (DOI o Handle) |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1881509005474398208 |
|---|---|
| author | Geraldo Campos, Luis Alberto Carreño-Flores, Oscar David Soria Quijaite, Juan Jesus |
| author_browse | Carreño-Flores, Oscar David Geraldo Campos, Luis Alberto Soria Quijaite, Juan Jesus |
| author_facet | Geraldo Campos, Luis Alberto Carreño-Flores, Oscar David Soria Quijaite, Juan Jesus |
| author_sort | Geraldo Campos, Luis Alberto |
| collection | Producción científica |
| description | The objective of this study was to analyze which machine learning models best predict mortgage payment difficulties in Peru.A quantitative method was used with longitudinal data from 2018 to 2022 from the National Household Survey (ENAHO), where a total of 5,716 households with mortgage loans were examined.The input variables considered were geographical area, type of housing, use of credit, and source of financing, with difficulty in meeting the payment schedule as the output variable.The analyses were performed in Google Colab, reporting frequency statistics and exploratory and class balancing analyses to evaluate machine learning models such as Logistic Regression, Random Forest (RF), and Support Vector Machine (SVM) with SMOTE.In the training phase of the classification models, the Scikit-learn, XGBoost, and Keras models were trained and compared.The results showed that, of all the models evaluated, Random Forest without adjustments showed the best performance (F1-score = 0.67; recall = 0.71), although combined Stacking (RF + XGBoost) showed a better balance between classes, but its overall performance was lower.In addition, models such as SVM without adjustments show problems in situations of unbalanced classes, highlighting the need to use techniques such as SMOTE.It is concluded that the Random Forest model is more effective in detecting payment difficulties in mortgage loans. |
| format | Article |
| id | oai:cris.upeu.edu.pe:20.500.15037/980 |
| institution | UPeU |
| language | English |
| publishDate | 2025 |
| publishDateRange | 2025 |
| publishDateSort | 2025 |
| record_format | dspace |
| spelling | oai:cris.upeu.edu.pe:20.500.15037/9802026-11-02T21:24:28ZMachine learning models for predicting mortgage payment difficulties in PeruGeraldo Campos, Luis AlbertoCarreño-Flores, Oscar DavidSoria Quijaite, Juan JesusThe objective of this study was to analyze which machine learning models best predict mortgage payment difficulties in Peru.A quantitative method was used with longitudinal data from 2018 to 2022 from the National Household Survey (ENAHO), where a total of 5,716 households with mortgage loans were examined.The input variables considered were geographical area, type of housing, use of credit, and source of financing, with difficulty in meeting the payment schedule as the output variable.The analyses were performed in Google Colab, reporting frequency statistics and exploratory and class balancing analyses to evaluate machine learning models such as Logistic Regression, Random Forest (RF), and Support Vector Machine (SVM) with SMOTE.In the training phase of the classification models, the Scikit-learn, XGBoost, and Keras models were trained and compared.The results showed that, of all the models evaluated, Random Forest without adjustments showed the best performance (F1-score = 0.67; recall = 0.71), although combined Stacking (RF + XGBoost) showed a better balance between classes, but its overall performance was lower.In addition, models such as SVM without adjustments show problems in situations of unbalanced classes, highlighting the need to use techniques such as SMOTE.It is concluded that the Random Forest model is more effective in detecting payment difficulties in mortgage loans.Articlehttps://laccei.org/LEIRD2025-Cartagena/full-papers/Contribution_105_final_a.pdfhttps://doi.org/10.18687/leird2025.1.1.10510.18687/leird2025.1.1.105https://hdl.handle.net/20.500.15037/980W4417244991enProceedings of the 5th LACCEI International Multiconference on Entrepreneurship, Innovation and Regional Development (LEIRD 2025): "Entrepreneurship with Purpose: Social and Technological Innovation in the Age of AI"2025-01-012026-06-13T09:42:13Z2026-06-13T09:42:13Z |
| spellingShingle | Geraldo Campos, Luis Alberto Carreño-Flores, Oscar David Soria Quijaite, Juan Jesus Machine learning models for predicting mortgage payment difficulties in Peru |
| title | Machine learning models for predicting mortgage payment difficulties in Peru |
| title_full | Machine learning models for predicting mortgage payment difficulties in Peru |
| title_fullStr | Machine learning models for predicting mortgage payment difficulties in Peru |
| title_full_unstemmed | Machine learning models for predicting mortgage payment difficulties in Peru |
| title_short | Machine learning models for predicting mortgage payment difficulties in Peru |
| title_sort | machine learning models for predicting mortgage payment difficulties in peru |
| url | https://laccei.org/LEIRD2025-Cartagena/full-papers/Contribution_105_final_a.pdf https://doi.org/10.18687/leird2025.1.1.105 https://hdl.handle.net/20.500.15037/980 |
| work_keys_str_mv | AT geraldocamposluisalberto machinelearningmodelsforpredictingmortgagepaymentdifficultiesinperu AT carrenofloresoscardavid machinelearningmodelsforpredictingmortgagepaymentdifficultiesinperu AT soriaquijaitejuanjesus machinelearningmodelsforpredictingmortgagepaymentdifficultiesinperu |