{rfName}
Ev

Indexed in

APC

0,00 Dollars

License and Use

Icono OpenAccess

Altmetrics

Analysis of institutional authors

Garcia-Dopico, AntonioAuthor

Share

July 31, 2025
Publications
>
Article
Sí

Evaluating the Performance of Deep Convolutional Neural Networks and Support Vector Regression for Creditworthiness Prediction in the Financial Sector

Publicated to: Inteligencia Artificial. 28 (76): 66-84 - 2025-12-01 28(76), DOI: 10.4114/intartif.vol28iss76pp66-84

Authors:

Kandi, K; García-Dopico, A
[+]

Affiliations

Univ Politecn Madrid, CCS Ctr Invest Simulac Comp, Madrid 28660, Spain - Author
Univ Politecn Madrid, DATSI Dept Arquitectura & Tecnol Sistemas Informat, Escuelta Tecn Super Ingn Informat, Madrid 28660, Spain - Author

Abstract

Creditworthiness prediction plays a crucial role in the financial sector, where accurate assessments of individuals' credit risk are essential for making informed lending decisions. In recent years, the use of advanced machine learning algorithms, such as Deep Convolutional Neural Networks (DCNNs) and Support Vector Regression (SVR), has gained traction for creditworthiness prediction tasks. These algorithms offer unique capabilities for analyzing complex financial data and extracting valuable insights to effectively assess credit risk. This study develops and compares credit risk prediction models using DCNNs and SVR, leveraging two real-world financial datasets: the Bank Churners Dataset (10,127 records, 23 features) from Kaggle and a Personal Loan Dataset (5,000 records, 14 features) with a significant class imbalance. The datasets include variables such as income, credit limit, transaction history, and loan acceptance, which are critical for assessing financial behavior. Given the imbalance in both datasets (e.g., only 16.1 % of customers churned in the Bank Churners Dataset and 10% accepted loans in the Personal Loan Dataset), we apply the Synthetic Minority Over-sampling Technique (SMOTE) to balance the classes and improve model performance. Evaluation metrics, including accuracy, precision, recall, and F1-score, demonstrate that SVR outperforms DCNN across key parameters, achieving an accuracy of 0.92, F1-score of 0.95, precision of 0.93, and recall of 0.97 on Dataset 1. In comparison, DCNN achieved an accuracy of 0.88, F1-score of 0.89, precision of 0.86, and recall of 0.91. On Dataset 2, while DCNN's accuracy improved to 0.93, SVR excelled with 0.98. These findings underscore the superiority of SVR in scenarios demanding high accuracy and precision, while DCNN offers a more balanced trade-off between precision and recall. This study provides actionable insights into selecting optimal models for credit risk evaluation, contributing to the development of reliable, data-driven financial systems.
[+]

Keywords

Complex networksConvolutional neural networkCredit risksCreditworthiness predictionDeep convolutional neural networkDeep learningEconomic and social effectsF1 scoresFinanceFinancial sectorsForecastingImbalanced datasetLearning algorithmsLearning systemsMachine learningMachine-learningPersonal loansRegression analysisRisk assessmentRisk perceptionSupport vector regressionSupport vector regressionsSynthetic minority over-sampling techniquesSynthetic minority oversampling technique

Quality index

Bibliometric impact. Analysis of the contribution and dissemination channel

The work has been published in the journal Inteligencia Artificial due to its progression and the good impact it has achieved in recent years, according to the agency WoS (JCR), it has become a reference in its field. In the year of publication of the work, 2025, it was in position 78/204, thus managing to position itself as a Q2 (Segundo Cuartil), in the category Computer Science, Artificial Intelligence. Notably, the journal is positioned en el Cuartil Q4 para la agencia Scopus (SJR) en la categoría Artificial Intelligence.

[+]

Impact and social visibility

From the perspective of influence or social adoption, and based on metrics associated with mentions and interactions provided by agencies specializing in calculating the so-called "Alternative or Social Metrics," we can highlight as of 2026-04-24:

  • The use of this contribution in bookmarks, code forks, additions to favorite lists for recurrent reading, as well as general views, indicates that someone is using the publication as a basis for their current work. This may be a notable indicator of future more formal and academic citations. This claim is supported by the result of the "Capture" indicator, which yields a total of: 17 (PlumX).

It is essential to present evidence supporting full alignment with institutional principles and guidelines on Open Science and the Conservation and Dissemination of Intellectual Heritage. A clear example of this is:

  • The work has been submitted to a journal whose editorial policy allows open Open Access publication.
  • Additionally, the work has been submitted to a journal classified as Diamond in relation to this type of editorial policy.
  • Assignment of a Handle/URN as an identifier within the deposit in the Institutional Repository: https://oa.upm.es/92918/

As a result of the publication of the work in the institutional repository, statistical usage data has been obtained that reflects its impact. In terms of dissemination, we can state that, as of

  • Views: 31
  • Downloads: 49
[+]

Leadership analysis of institutional authors

There is a significant leadership presence as some of the institution’s authors appear as the first or last signer, detailed as follows: First Author (KANDI, KIANEH) and Last Author (GARCIA DOPICO, ANTONIO).

the author responsible for correspondence tasks has been KANDI, KIANEH.

[+]

Project objectives

Los objetivos perseguidos en esta aportación se centran en mejorar la predicción de la solvencia crediticia mediante técnicas avanzadas. Se pretende analizar el desempeño de redes neuronales convolucionales profundas (DCNN) y regresión por vectores de soporte (SVR) en la predicción del riesgo crediticio. Evaluar modelos utilizando dos conjuntos de datos financieros reales con desequilibrio de clases. Aplicar la técnica SMOTE para equilibrar las clases y optimizar el rendimiento de los modelos. Comparar métricas de evaluación como precisión, exactitud, recall y F1-score para determinar el modelo más eficaz. Proporcionar recomendaciones para la selección de modelos óptimos en sistemas financieros basados en datos.
[+]

Most relevant results

Los resultados más relevantes del estudio se centran en la comparación del desempeño de modelos de Deep Convolutional Neural Networks (DCNN) y Support Vector Regression (SVR) para la predicción de solvencia crediticia en dos conjuntos de datos financieros reales. En el Bank Churners Dataset, SVR alcanzó una precisión de 0.92, F1-score de 0.95, precisión de 0.93 y recall de 0.97, superando a DCNN que obtuvo 0.88, 0.89, 0.86 y 0.91 respectivamente. En el Personal Loan Dataset, DCNN mejoró su precisión a 0.93, pero SVR destacó con una precisión de 0.98. La aplicación de SMOTE permitió equilibrar las clases en ambos conjuntos, mejorando el rendimiento de los modelos. Estos resultados evidencian la eficacia superior de SVR en precisión y exactitud.
[+]