Parvaneh Salatin, Mahdi Molania, Mahmood Mahmoodzadeh, Mohammad Hosein Fatehi,
Volume 14, Issue 53 (12-2023)
Abstract
Today, information and communication technology affects all aspects of human life. The result of which is a transformation in all methods of production and distribution to education, exchanges and human relations. On the other hand, the requirement for the realization of economic development and growth is the higher growth rate in poor and underdeveloped areas than in rich and developed areas, which is proposed as the hypothesis of convergence. In this regard, regional inequalities are a fundamental challenge for the development of regions and these inequalities are a serious threat to create a balanced development of regions. Therefore, the main goal of the current study is to investigate the convergence of Fava among the provinces of the country. The results using the Nahar and Inder method during the period of 2002-2013 showed that out of the 30 investigated provinces, divergence in land use occurred in 22 provinces. Also, at the infrastructure level, the average slope of 31 provinces is positive, but the t-value is significant for the provinces of South Khorasan, Khuzestan, Alborz and Fars, which shows that digital divergence has occurred in these provinces during the period under review. Therefore, it can be seen that although in terms of infrastructure, we have had less divergence at the level of the provinces, but in terms of usage, this gap and divergence has increased.
|
Mahmood Mahmoodzadeh, Masood Soufi, Morteza Alipour,
Volume 16, Issue 60 (9-2026)
Abstract
Despite the growing use of machine learning in credit scoring, many domestic studies still rely mainly on traditional statistical models and static borrower characteristics, while limited attention has been paid to the role of real behavioral, transactional, and repayment-performance data in post-disbursement credit risk monitoring. To address this research gap, this study compares the performance of four stepwise logistic regression models and the LightGBM algorithm in predicting credit default, using data from 119,050 loan facilities granted to individual customers of Resalat Qard al-Hasan Bank during the period between 26 March 2022 and 18 March 20240. The target variable was defined based on repayment delays of more than 90 days, and model performance was evaluated using AUC, Accuracy, Recall, F1-Score, and Balanced Accuracy. The knowledge contribution of this study lies in providing empirical evidence on the effectiveness of real banking data, focusing on behavioral and transactional variables, comparing a classical statistical model with a machine learning algorithm, and assessing model performance in identifying the minority class under imbalanced credit data. The results indicate that repayment-related variables, particularly the number of overdue installments and outstanding debt balance, are the most important predictors of default. Although the fourth logistic regression model achieved a high overall AUC of 0.98, it performed poorly in identifying high-risk customers, with a Recall of only 0.12%. In contrast, LightGBM identified 92.2% of high-risk customers and outperformed logistic regression on imbalance-sensitive evaluation metrics. These findings suggest that, in imbalanced credit datasets, relying solely on AUC and Accuracy can be misleading, while Recall, F1-Score, and Balanced Accuracy are more informative for assessing a model’s ability to detect high-risk borrowers. Therefore, in the post-disbursement monitoring scenario, machine learning algorithms based on behavioral and transactional data can provide a more accurate and reliable framework for credit risk management in Iranian banks.
