Abstract
This research focuses on predicting loan defaults using big data analytics machine learning models applied to a comprehensive loan dataset. The analysis is conducted using R statistical software, enabling data-driven insights for enhanced credit risk management. Three algorithms Random Forest, XGBoost, and Naïve Bayes are implemented to determine the most effective predictive model and identify key risk factors. The study utilized a comprehensive loan dataset sourced from Kaggle which comprised of 148,670 individual loan records, each characterized by 34 features spanning borrower demographics, financial characteristics, and loan specifications. Feature selection followed a multi-stage process designed to optimize model performance while maintaining interpretability. The balanced dataset (73,278) was partitioned using stratified random sampling to ensure representative class distribution. Model performance was assessed using multiple metrics to provide a comprehensive evaluation. XGBoost emerged as the optimal algorithm, achieving 80.5% accuracy through its sophisticated gradient-boosting framework and robust handling of class imbalance. The research establishes several key contributions to the field of credit risk modeling.
Keywords
Loan Predicting, Loan Defaults, Big Data, Machine Learning, Random Forest, XGBoost, and Naïve Bayes
Citations
IRE Journals:
Uchenna Emmanuel Evans-Anoruo
"Predicting Loan Defaults Using Big Data Analytics and Machine Learning" Iconic Research And Engineering Journals Volume 9 Issue 2 2025 Page 1258-1264
IEEE:
Uchenna Emmanuel Evans-Anoruo
"Predicting Loan Defaults Using Big Data Analytics and Machine Learning" Iconic Research And Engineering Journals, 9(2)
About IRE Journals
IRE Journals is an open access online journals established with an aim to publish high quality of research work in various diciplines. We have more than 6 years in publications. Over 2500+ papers already published.
Important Links
For Authors
Volume 8:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 7:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 6:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 5:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 4:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 3:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12