Showing 3 results for Alipour
Morteza Chashti, Mohammad Reza Lotfalipour, Mehdi Behname, Taghi Enrahimi Salari,
Volume 10, Issue 37 (10-2019)
Abstract
International balance of payments is one of the most common criteria for measuring the flow of trade and capital transfers in an open economy. The three main components of this balance are: trade balance, current account (or difference between export and import of goods and services) and capital account. In this study, factor augmented vector autoregressive model (FAVAR) was used to evaluate the effects of balance of payments shocks on macroeconomic variables in the Iran economy in periode 1989-2017. The factors used in this study included economic growth, oil revenues, money growth, inflation, exchange rates and interest rates. The results show that the shock from the current account and capital account led to an increase in production, consumption and investment. The reaction of nominal sector variables such as inflation and interest rate to positive shock was also positive. Comparison of the results of this study shows that incorporation of hidden variables and factors into the model resulted in faster response of macroeconomic variables to the shocks entered by the balance of payments components.
Vahid Rezaei, Mohammad Reza Lotfalipour, Seyed Saeed Malek Sadati, Narges Salehnia,
Volume 16, Issue 59 (5-2025)
Abstract
Inflation, as a key indicator of economic performance, directly affects household purchasing power, price stability, and the long-term planning of firms and governments. Uncontrolled inflation not only reduces public welfare and exacerbates social inequalities, but also disrupts investment and sustainable growth by creating instability in economic expectations. Therefore, identifying the drivers of inflation and understanding their transmission mechanisms is essential for designing effective monetary and fiscal policies. This study investigates the impact of economic shocks on the inflation rate by employing a combination of two approaches: first, the random forest-based variable selection method with recursive feature elimination (RF-RFE) to identify the most influential factors, and second, the Bayesian vector autoregression (BVAR) model to analyze the time dynamics and mutual interactions of these shocks.The dataset covers 42 economic variables from the first quarter of 2009 to the fourth quarter of 2021, grouped into seven categories: supply, demand, monetary and banking, taxation and budget, exchange rate, energy, and employment. In the first step, the RF-RFE method identified the most important determinants of consumer inflation. The results indicated that five key variables producer inflation, value added in the oil and gas sector, quasi-money, the market exchange rate, and banknotes and coins in circulation play a major role in explaining consumer price fluctuations.The subsequent BVAR analysis showed that shocks originating from producer inflation and the exchange rate exert strong short-term effects on consumer inflation. By contrast, variables such as oil and gas value added play a moderating role in the long term, gradually alleviating inflationary pressures. Furthermore, the variance decomposition of forecast errors suggests that, in the long run, exchange rate volatility and liquidity changes driven by quasi-money increasingly account for fluctuations in inflation
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.
