Asset-Liability Management (ALM) of banks is defined as simultaneous planning of all bank assets and liabilities under different conditions and its purpose is to maximize profits and minimize the risks in banks by optimizing the parameters in the balance sheet. Most of the studies `and proposed models in the ALM field are based on an objective function that maximizes bank profit. It is not easy to apply changes in these models in order to reach the optimal values of the parameters in the balance sheet. In this article, an attempt has been made to propose a linear model using constraints to achieve optimal values of balance sheet parameters using ALM objectives and considering balance sheet, system and regulatory constraints. It has also been tried to design the model according to the most possible mode and with the least changes and to minimize the size of the balance sheet. The analysis of the model presented in this article has been conducted using the parameters of the balance sheet and income statement of one of the famous Iranian banks. The results obtained from the proposed model show that the values of cash and receivables from banks and other credit institutions have decreased by 30% and increased by 200%, respectively, compared to the actual values of these parameters. Also, Total Income, Operating Income and Non-Operating Income have grown by 30% compared to the actual values of these parameters. Also, the values of a number of parameters are estimated to be zero after optimization. According to the results, it is obvious that the performance of bank managers, especially in the management of bank assets, is significantly different from the optimal values of the balance sheet, and the results obtained from the proposed model can help the management of banks as much as possible.

Classifying imbalanced data is a well-known challenge in machine learning. One of the fields inherently affected by imbalanced data is credit datasets in finance. In this study, to address this challenge, we employed one of the most recent methods developed for classifying imbalanced data, CorrOV-CSEn. In addition to the original CorrOV-CSEn approach, which uses AdaBoost as its base learning method, we also applied Multi-Layer Perceptron (MLP), random forest, gradient boosted trees, XGBoost, and CatBoost. Our dataset, sourced from the Iran capital market from 2015 to 2022, utilizes the more general and accurate term business failure instead of default. Model performance was evaluated using sensitivity, precision, and F1 score, while their overall performance was compared using the Friedman–Nemenyi test. The results indicate the high effectiveness of all models in identifying failing businesses (sensitivity), with CatBoost achieving a sensitivity of 0.909 on the test data. However, all models exhibited relatively low precision.

Economic policies aimed at managing economic variables in the short and long term have always been of special importance. These policies seek to reduce economic fluctuations in the short term and increase sustainable economic growth in the long term. One of these policies is monetary policy, which is mainly carried out by central banks worldwide. This paper uses the Keynesian Dynamic Stochastic General Equilibrium (DSGE) model to examine the effects of monetary policy on the real variables of the Iranian economy through the credit channel and the balance sheet channel. The presented model analyzed information about macroeconomic variables in Iran for the period from 1990 to 2020. The obtained results show that with the implementation of restrictive monetary policy in the economy, all productive activities of enterprises decreased, and this led to a decrease in household income, which in turn reduced household savings in the form of bank deposits. Because the most important sources of financing for banks are deposits, the ability of banks to offer loans was reduced. On the other hand, a restrictive monetary shock was associated with a decline in the value of corporate securities. As a result, the amount of received loans by firms was reduced by the value of the assets. This reduced the demand of banks for bank loans, which intensified the effects of the initial shock, along with a reduction in the banks’ ability to provide lending services. Further, the results indicate the relative success of the model in simulating Iran’s macro economy.

In the aftermath of global financial crises and amid increasing complexity in banking operations, understanding and managing various types of risk—especially liquidity, credit, and solvency risks—has become a global concern for financial stability. This study addresses a critical gap in the literature by examining the dynamic interrelationships among these three types of risk in the context of emerging markets. Using data from 21 banks listed on the Iranian capital market from 2011 to 2023, we employ a Panel Vector Error Correction Model (VECM) alongside panel impulse response analysis to assess both short- and long-term dynamics. Our results reveal that an increase in liquidity positively impacts bank solvency, while credit risk negatively affects solvency but does not significantly influence liquidity risk. These findings contribute to the theoretical understanding of systemic risk interactions in banking and provide practical insights for policymakers and financial institutions seeking to enhance risk management strategies in volatile market environments.

This study evaluates the economic capital levels for Iranian banks and analyzes their behavior under various macroeconomic shocks by developing a Dynamic Stochastic General Equilibrium (DSGE) model that incorporates banking sector heterogeneity and macroeconomic shock transmission mechanisms. A comprehensive DSGE framework was constructed and calibrated using Iranian macroeconomic and banking data. The ...