Machine Learning and Deep Learning for Loan Prediction in Banking: Exploring Ensemble Methods and Data Balancing

The prediction of loan defaults is crucial for banks and financial institutions due to its impact on earnings, and it also plays a significant role in shaping credit scores. This task is a challenging one, and as the demand for loans increases, so does the number of applications. Traditional methods...

Full description

Saved in:
Bibliographic Details
Main Authors: Eslam Hussein Sayed, Amerah Alabrah, Kamel Hussein Rahouma, Muhammad Zohaib, Rasha M. Badry
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10772107/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850242839352442880
author Eslam Hussein Sayed
Amerah Alabrah
Kamel Hussein Rahouma
Muhammad Zohaib
Rasha M. Badry
author_facet Eslam Hussein Sayed
Amerah Alabrah
Kamel Hussein Rahouma
Muhammad Zohaib
Rasha M. Badry
author_sort Eslam Hussein Sayed
collection DOAJ
description The prediction of loan defaults is crucial for banks and financial institutions due to its impact on earnings, and it also plays a significant role in shaping credit scores. This task is a challenging one, and as the demand for loans increases, so does the number of applications. Traditional methods of checking eligibility are time-consuming and laborious, and they may not always accurately identify suitable loan recipients. As a result, some applicants may default on their loans, causing financial losses for banks. Artificial Intelligence, using Machine Learning and Deep Learning techniques, can provide a more efficient solution. These techniques can use various classification algorithms to predict which applicants will likely be eligible for loans. This study uses five Machine Learning classification algorithms (Gaussian Naive Bayes, AdaBoost, Gradient Boosting, K Neighbors Classifier, Decision Trees, Random Forest, and Logistic Regression) and eight Deep Learning algorithms (MLP, CNN, LSTM, Transformer, GRU, Autoencoder, ResNet, and DenseNet). The use of Ensemble Methods and SMOTE with SMOTE-TOMEK Techniques also has a positive impact on the results. Four metrics are used to evaluate the effectiveness of these algorithms: accuracy, precision, recall, and F1-measure. The study found that DenseNet and ResNet were the most accurate predictive models. These findings highlight the potential of predictive modeling in identifying credit disapproval among vulnerable consumers in a sea of loan applications.
format Article
id doaj-art-94ab608b561a4bbaa9fa66e7cc778342
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-94ab608b561a4bbaa9fa66e7cc7783422025-08-20T02:00:10ZengIEEEIEEE Access2169-35362024-01-011219399719401910.1109/ACCESS.2024.350977410772107Machine Learning and Deep Learning for Loan Prediction in Banking: Exploring Ensemble Methods and Data BalancingEslam Hussein Sayed0https://orcid.org/0009-0007-0909-1702Amerah Alabrah1https://orcid.org/0000-0001-9750-3883Kamel Hussein Rahouma2Muhammad Zohaib3Rasha M. Badry4https://orcid.org/0000-0002-8094-5930Information System Department, Faculty of Computers and Information, Fayoum University, Faiyum, EgyptDepartment of Information Systems, College of Computer and Information Science, King Saud University, Riyadh, Saudi ArabiaElectrical Engineering Department, Faculty of Engineering, Minia University, Minya, EgyptSoftware Engineering Department, Lappeenranta-Lahti University of Technology, Lappeenranta, FinlandInformation System Department, Faculty of Computers and Information, Fayoum University, Faiyum, EgyptThe prediction of loan defaults is crucial for banks and financial institutions due to its impact on earnings, and it also plays a significant role in shaping credit scores. This task is a challenging one, and as the demand for loans increases, so does the number of applications. Traditional methods of checking eligibility are time-consuming and laborious, and they may not always accurately identify suitable loan recipients. As a result, some applicants may default on their loans, causing financial losses for banks. Artificial Intelligence, using Machine Learning and Deep Learning techniques, can provide a more efficient solution. These techniques can use various classification algorithms to predict which applicants will likely be eligible for loans. This study uses five Machine Learning classification algorithms (Gaussian Naive Bayes, AdaBoost, Gradient Boosting, K Neighbors Classifier, Decision Trees, Random Forest, and Logistic Regression) and eight Deep Learning algorithms (MLP, CNN, LSTM, Transformer, GRU, Autoencoder, ResNet, and DenseNet). The use of Ensemble Methods and SMOTE with SMOTE-TOMEK Techniques also has a positive impact on the results. Four metrics are used to evaluate the effectiveness of these algorithms: accuracy, precision, recall, and F1-measure. The study found that DenseNet and ResNet were the most accurate predictive models. These findings highlight the potential of predictive modeling in identifying credit disapproval among vulnerable consumers in a sea of loan applications.https://ieeexplore.ieee.org/document/10772107/Customer loan predictionartificial intelligencedata preprocessingmodel optimizationmachine learningdeep learning
spellingShingle Eslam Hussein Sayed
Amerah Alabrah
Kamel Hussein Rahouma
Muhammad Zohaib
Rasha M. Badry
Machine Learning and Deep Learning for Loan Prediction in Banking: Exploring Ensemble Methods and Data Balancing
IEEE Access
Customer loan prediction
artificial intelligence
data preprocessing
model optimization
machine learning
deep learning
title Machine Learning and Deep Learning for Loan Prediction in Banking: Exploring Ensemble Methods and Data Balancing
title_full Machine Learning and Deep Learning for Loan Prediction in Banking: Exploring Ensemble Methods and Data Balancing
title_fullStr Machine Learning and Deep Learning for Loan Prediction in Banking: Exploring Ensemble Methods and Data Balancing
title_full_unstemmed Machine Learning and Deep Learning for Loan Prediction in Banking: Exploring Ensemble Methods and Data Balancing
title_short Machine Learning and Deep Learning for Loan Prediction in Banking: Exploring Ensemble Methods and Data Balancing
title_sort machine learning and deep learning for loan prediction in banking exploring ensemble methods and data balancing
topic Customer loan prediction
artificial intelligence
data preprocessing
model optimization
machine learning
deep learning
url https://ieeexplore.ieee.org/document/10772107/
work_keys_str_mv AT eslamhusseinsayed machinelearninganddeeplearningforloanpredictioninbankingexploringensemblemethodsanddatabalancing
AT amerahalabrah machinelearninganddeeplearningforloanpredictioninbankingexploringensemblemethodsanddatabalancing
AT kamelhusseinrahouma machinelearninganddeeplearningforloanpredictioninbankingexploringensemblemethodsanddatabalancing
AT muhammadzohaib machinelearninganddeeplearningforloanpredictioninbankingexploringensemblemethodsanddatabalancing
AT rashambadry machinelearninganddeeplearningforloanpredictioninbankingexploringensemblemethodsanddatabalancing