Iranian Journal of Finance

Abstract In today's complex economic landscape, accurately predicting events such as customer loan defaults presents a significant challenge for financial institutions. Traditional methods have shown limitations in accuracy, prompting the adoption of data-driven machine learning techniques for enhanced predictive capabilities. This study investigates the efficacy of novel machine-learning algorithms compared with linear models for predicting loan defaults at a major commercial bank. Data from over six thousand customer loan files spanning 2019 to 2022 were collected, cleaned, and clustered based on key loan indicators. The accuracy of predicting loan defaults was first evaluated using popular machine learning classification models, including LightGBM, XGBoost, Multilayer Perceptron, and Logistic Regression, and XGBoost performed best. After that, prediction accuracy was evaluated using various time-series machine learning algorithms, with a particular focus on a combined Gradient Boosting and Long Short-Term Memory (LSTM) approach. Results indicate that the combined algorithm outperforms traditional linear models, showing a substantial 40% improvement over the ARIMA algorithm in predicting loan default behavior. This study underscores the potential of advanced machine learning techniques to enhance predictive accuracy in the banking sector, offering valuable insights for risk assessment and financial decision-making.

Abstract One of the main demands of investors (depositors and shareholders) of banks is transparency. However, in addition to the requirements for meeting this demand, measuring how to meet it has become challenging. So far, researchers have proposed different qualitative criteria for transparency. In this study, while introducing the correlation coefficient between book and market value at risk (VaRs) as a criterion of transparency, we seek to examine the stability of this criterion in different economic conditions. For this purpose, first, by using the e-garch model, the value at risk was estimated based on the balance sheet (book) information and also the market information of the banks' shares, then by calculating the correlation coefficients between book and market VaR’s under normal conditions, we predict book and market VaR’s using vector auto-regressive (VAR) models, along with defining three stress scenarios (Mild - Severe - hyper stress). We examined the significance of the difference between the calculated correlation coefficients in the three stress test modes. We thus tested the stability of the correlation coefficient of the defined scenarios. The findings showed that except for the correlation caused by the unemployment rate factor in mild and hyper-stress scenarios, in other cases, no evidence of H0 rejection was found, indicating the stability of the correlation coefficient between book and market VaRs as a measure of transparency.

Abstract "Corporate governance" includes mechanisms to monitor CEO's performance to assure efficient decision adoption and maximize firm value. One of the most effective aspects of firm performance is the degree of risk-taking. This study investigates the relationship between CEO power and institutional ownership with risk-taking behavior of member firms of Tehran Stock Exchange and Iran Fara Bourse during 2010-2019 by utilizing quintile regression. According to the results, by the increase of CEO's power and the company's benefit from powerful managers, the company risk (total risk and systemic risk) will decrease. As a result, managers are eager to safeguard their reputation as expert decision-makers and, as a result, they try to reduce company risk. In addition, the existence of institutional ownership among the shareholders of the company will reduce the risk, which can be referred to in the agency theory. Also, if the impact of these two variables is considered together, the risk will increase significantly. This very fact reflects the exercise of the power and influence of institutional owners. As a result, large shareholders have a supervisory role in the discipline of managers, but despite their impact on the relationship between managers' power and corporate risk, they do not alter the main negative relationship.

Abstract This paper concentrates on the modelling of optimal stock portfolio selection based on Risk Assessment and Behavioral Financial Approach Mental Accounting and 28 expert’s opinion. In this approach developing the model approved by the opinion of academic and practical experts using quantitative and qualitative methods.  Using quarterly return data of industrial indices for ten years in form of eight training and two test years indicates that the performance of DMSS and MVO based portfolios is equal however by regarding the value at risk and liquidity constraints in modeling, DMSS based portfolios perform higher than MVO portfolios.

Abstract Nowadays, financial markets in Iran have attracted the attention of many managers, investors and financial policymakers. Therefore, in order to make the optimal decision and reduce the risks in such a market, it is important to identify and analyze the network behavior of the financial markets at different times to obtain the optimal decision. The current study aims to answer the following research question; how is it possible to use the minimum spanning tree and hierarchical clustering in the network analysis of the Tehran Stock Exchange? The period examined was 2013 to 2018. The population consisted of all the companies accepted in Tehran Stock Exchange. The sampling was selected purposefully and contained the companies which had at least one trading day in the time span from the beginning of 2013 to the end of 2018. The stock of the investigated companies was considered as the vertexes of one graph and the coherent information criterion was considered as the weight of the edge. First, the minimum spanning tree of the graph was calculated. The results revealed that the stocks of DarooAbuReihan, DarooPakhsh and Alborzdaroo had a high influence on directing the prices of the other stocks. Furthermore, the results of hierarchical clustering classified the stocks of the companies into 8 clusters. This study presents a viewpoint about the modern method designed for the analysis of complex financial networks. Moreover, the study offers an analysis of Iran's stock market structure which can be the center of finance researchers and analysts' attention.

Abstract Market participants use different tools basically technical or fundamental analysis to have a higher return in constructing a well-maintained portfolio. Examining the efficiency of technical strategies in creating a portfolio is the main objective of this study. Technical analysis is based on using historical trading data to launch selling and buying rules that maximize return and still control risks of loss. We use the adjusted trading data of 50 active stocks in the Tehran Stock Exchange as our sample which includes daily trading data from 2008 to 2019. We construct two types of portfolio; strategy-based portfolio versus random one. Then we calculate abnormal returns of each type of portfolio, applying the Monte-Carlo technique. Using Independent-Samples T-Test to compare means of the abnormal returns, our findings show that there is a significant positive abnormal return for both strategies applied in constructing a portfolio (0.057 and 0.062 mean difference for the first and second strategy, respectively), confirming the higher efficiency of applying technical strategies in portfolio management. Therefore, it is suggested to have and apply a strategy or combination of strategies for trading as an active participant, instead of constructing, rebalancing and maintaining one’s portfolio only by chance, since there will be undesirable results in the long-run.

Abstract Asset-liability management (ALM) helps managers achieve their respective objectives by surveilling and controlling the ways through which resources are obtained and allocated. Furthermore, with the help of liquidity management, which sets the required cash by banks for fulfilling costs and other needs (e.g. the cash requested by depositors), ALM controls the risk. In addition, ALM helps managers realize profitability and efficiency of the bank through the application of goal programming (GP) whereby multiple objectives are simultaneously considered when making decisions.
In the present research, upon collecting the required data and information, acquiring opinions of experts at a sample bank, and investigating balance sheet of the bank while considering respective constraints, orders of priority of objectives were determined. The results indicated consistency of some items in the balance sheet, such as cash inventory and liability to Central Bank with those set by the model. On the other hand, when it came to some other items, including receivables from the government and credited facilities to public sector, the observed growth was in line with that anticipated by the model. In the meantime, for most items of the balance sheet, including termed deposits and other deposits, investments, and joint activities, the model suggested variable yet positive growths; the growth was higher in demand deposits which are known as less expensive resources, indicating facts about Iranian banking system and Iranian economy where communities are making greater deals of effort to attract this sort of resource.