درخت حوزه‌های تخصصی

This study seeks to rigorously assess the relationship between Iran’s stock market index and monetary policy within the framework of the Markov Switching Vector Autoregressive (MS-VAR) model. The MS-VAR methodology is particularly well-suited for capturing regime-dependent dynamics and structural shifts in macroeconomic and financial time series. For this purpose, quarterly data spanning from Spring 2009 to Fall 2023 have been employed. All estimations were conducted using EViews 12 and OX Metrics 7 software. As a preliminary step, the Hodrick-Prescott filter was applied to differentiate between two distinct market regimes. Combined with a univariate Markov Switching model, this approach enabled the identification of cyclical fluctuations in the stock market, distinguishing bull from bear market phases. The results indicate that Regime 1 (bear market) demonstrates greater persistence and stability relative to Regime 2 (bull market), suggesting asymmetric market dynamics. Subsequently, the study investigates the effects of monetary policy—proxied by the interbank market rate and liquidity growth—on the growth of the stock market index within the MS-VAR framework. The findings suggest that monetary policy has different effects during bull and bear market phases. The stock index exhibits a prompt and asymmetric response to changes in both the interbank market rate and liquidity growth. Specifically, in both bull and bear market regimes, an increase in the interbank interest rate exerts a contractionary effect on stock index growth, with a more pronounced negative impact observed during periods of market recession. Moreover, liquidity growth consistently contributes positively to stock index growth across both regimes, with a more pronounced effect under bull market conditions. Variance decomposition analysis further reveals that, in both regimes, shocks to the stock index itself account for the largest proportion of its fluctuations. Nonetheless, the relative importance of monetary policy instruments varies by regime: In both expansionary and recessionary phases of the stock market, shocks stemming from the interbank market rate play a more prominent role in explaining stock index volatility compared to liquidity shocks. Finally, the presence of nonlinear interactions among the variables is statistically validated based on the Likelihood Ratio (LR) test.

Detecting financial fraud is an important process in the activities of compa-nies. In the last decade, much attention has been paid to fraud detection techniques. Financial fraud is a problem with far-reaching implications for shareholders. Today, financial fraud in companies has become a big prob-lem. Companies and regulatory agencies must continuously develop their mechanisms to detect fraud. Machine learning and data mining techniques are currently commonly used to solve this problem. However, these tech-niques still need to be improved in terms of computational cost, memory cost, and dealing with big data that is becoming a feature of current financial transactions. In this research, machine learning techniques including logistic regression, neural network, and Bayesian linear regression were used to de-tect financial frauds in the Iranian stock market. According to the obtained results, the support vector machine model with radial kernel has the lowest RMSE and the highest accuracy criterion, and the support vector machine model with linear kernel and Bayesian linear regression has the highest RMSE and the lowest accuracy criterion for modeling the financial fraud of companies in they were Tehran stock market. Also, the models of artificial neural network model, Bayesian linear regression and support vector ma-chine model with linear kernel respectively had the lowest characteristic values and did not perform relatively well in detecting the existence of fi-nancial fraud in the companies present in the Tehran stock market.