Iranian Journal of Finance

Abstract This study examines the key drivers of the Islamic debt securities market (Sukuk). This Sharia-compliant financial instrument is gaining recognition for its role in promoting economic development through ethical, non-usurious financing. As it is being used more in sectors such as infrastructure, energy, housing, and development, Sukuk has emerged as a significant financing tool for both Islamic and international markets. Following a two-step research strategy, the study first identified and categorized key factors influencing Sukuk market development by conducting a qualitative analysis of academic literature, scientific reports, and institutional documents. Twenty-one main components were distilled at this stage. Experts' views were gathered and analyzed at the second stage, based on linguistic variables, a fuzzy ranking technique, and Excel-based modelling, to prioritize factors uncovered while managing uncertainty in expert judgment. The results indicate that increasing the liquidity of Islamic finance instruments is the most significant method for improving Sukuk market growth, followed by the Management of Issuance Costs of Islamic Financial Securities (Sukuk) and Risk management (including exchange rate, interest rate, and credit risk) within the Sukuk structure. The study offers policy relevance to policymakers, regulators, and stakeholders who aim to improve the Islamic finance ecosystem by promoting the development and efficiency of the Sukuk market through targeted, evidence-based policies.

Abstract Many researchers have attempted to explain the phenomenon of medium-term return continuation using modern financial theories. The excess return gained in the momentum investment strategy, in fact, compensates for unknown risks that current theories are unable to explain. Research indicates that various strategies can be beneficial at different maintenance periods. Various strategies generally involve a simple method in which they are formed based on the criterion of return over a certain period in the past and are maintained for a corresponding period in the future. Each investment strategy tends to generate excess returns based on the predictability of short-term price movements, as indicated by past performance. The purpose of this study is primarily to investigate the usefulness of residual momentum and conventional momentum strategies in the short-term and long-term. The time period of this study is from 2009 to 2018, and the general approach for calculations is based on the method described by Jegadeesh and Titman (1993), Blitz et al. (2011), and Blitz et al. (2020). The results of this study show no significant difference between residual and conventional momentum strategies in both short-term and long-term periods, indicating that both approaches exhibit similar risk-adjusted performance and forecasting capabilities.

Abstract In an increasingly volatile and uncertain financial landscape, particularly within the cryptocurrency market, robust risk assessment methods are essential. This study introduces an interdisciplinary framework that applies engineering concepts, specifically the three-sigma (3σ) criterion, to financial asset management. Drawing on the analogy between structural stress and financial return volatility, this study conceptualizes market returns as a stochastic stress process and asset strength as a dynamically adjusted resilience threshold. Using LUNA coin as a case study, the research employs Monte Carlo simulations, statistical process control principles, and a range of statistical tests, including the Shapiro-Wilk, Kolmogorov–Smirnov, and ANOVA tests, to evaluate the probability of structural failure, modeled as the first passage beyond a critical return threshold. The results reveal a first breach probability of 1.96% and identify a failure threshold of –0.3838, highlighting the model's capacity to detect extreme downside risk more conservatively than traditional Value-at-Risk (VaR) approaches. These findings support the use of three-sigma thresholds in highly volatile markets and align with previous studies emphasizing tail-risk modeling and engineering-inspired risk measures. This framework not only improves the understanding of asset fragility in crypto markets but also provides a practical tool for dynamic and real-time risk management. This study contributes to the evolving field of financial engineering by bridging statistical design principles and asset resilience modeling, offering new insights for researchers, investors, and policymakers.

Abstract This study examines the integration of machine learning techniques with smart beta investment strategies to enhance portfolio performance. Traditional market indices often fail to meet investors' expectations, especially during volatile market periods, leading to a growing interest in alternative strategies such as smart beta methodologies. These strategies combine the cost and risk efficiency of passive investing with the performance advantages of active strategies by employing alternative weighting schemes based on financial factors such as value, quality, and momentum. In this research, Return on Invested Capital (ROIC) is selected as a value-based factor due to its strong reflection of a company's operational efficiency and value creation driver. We employ three machine learning models—Support Vector Regression (SVR), Random Forest, and XGBoost—to forecast ROIC based on various financial ratios. Each model is fine-tuned using Bayesian optimization techniques to achieve the highest forecasting accuracy. The dataset includes financial data from 85 manufacturing companies listed on the Tehran Stock Exchange. Model performance is evaluated using R², Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE), with the optimized Random Forest model achieving the best results based on higher R² and lower error values compared to the other models. The forecasted ROIC values are then used to construct a smart beta portfolio, which is compared to a traditional market-cap-weighted portfolio. The findings demonstrate that a machine learning-enhanced, ROIC-based smart beta strategy can significantly outperform traditional approaches, offering investors a more robust and data-driven method for portfolio construction and risk-adjusted return enhancement.

Abstract The primary objective of this study is to develop a predictive model for money laundering risk in Iranian listed firms. Initially, firm-level money laundering risk is measured using auditor assessments of anti-money laundering (AML) activities disclosed in annual audit reports. Subsequently, a quantitative modeling approach is employed, using financial and governance-related variables identified in prior research. To validate the quantitative findings, a qualitative approach based on grounded theory is also applied to identify additional explanatory factors. This research follows a mixed-methods design, incorporating both quantitative and qualitative phases. In the quantitative phase, a panel logit regression model is estimated using data from 1,680 firm-year observations covering the period 2012–2023. Independent variables include firm size, return on equity, leverage, investment opportunities, board independence, and board size. In the qualitative phase, semi-structured interviews were conducted with 10 experts to identify key risk factors, followed by the design and administration of an 18-item questionnaire distributed to 110 professionals. Exploratory factor analysis was then used to extract latent variables. The quantitative analysis reveals significant relationships between money laundering risk and several variables, such as firm size (positive), return on equity (negative), leverage (positive), and board independence (negative). The qualitative analysis identifies three core factors: (1) organizational culture and employee training, (2) corporate governance, and (3) a composite factor comprising compliance, organizational complexity, financial performance, firm size, and capital structure. Together, these factors explain over 50% of the variance in expert responses. The convergence of results from both methodological approaches confirms the robustness of the proposed model. Corporate governance indicators—particularly board size and independence—alongside financial attributes such as firm size, profitability, and capital structure, are found to be significant predictors of firm-level money laundering risk. The findings underscore the importance of strengthening internal control mechanisms and compliance structures in reducing money laundering risk.

Abstract The main objective of this study is to compare the predictive accuracy of machine learning models, particularly Random Forest and Artificial Neural Networks, with classical statistical methods (such as Logistic Regression and Linear Discriminant Analysis) in forecasting the risk of Exchange-Traded Funds (ETFs) in member countries of the Federation of European and Asian Stock Exchanges. Furthermore, the study aims to identify the key performance and fundamental variables impacting the risk of these funds. This research adopts a quantitative approach based on secondary data analysis. Data were collected for the years 2015-2023 from the databases of the Federation of European and Asian Stock Exchanges and the Tehran Stock Exchange. After preprocessing, risk prediction models, including Random Forest, Artificial Neural Networks, Logistic Regression, and Linear Discriminant Analysis, were developed and validated for each country using unified evaluation metrics (such as accuracy and AUC). The statistical significance of differences in model performance was tested using non-parametric Mann-Whitney U tests, given the non-normal distribution of accuracy across countries. Sensitivity analysis was then conducted on the two superior machine learning models to determine the impact of independent variables (both performance indicators, such as Jensen's alpha and market return, and fundamental attributes, such as fund size and manager expertise) across different markets. Empirical results indicate that, across most countries and after harmonizing time and geographical dimensions, machine learning models, specifically Random Forest and Artificial Neural Networks, outperform classical statistical approaches in predicting ETF risk, with statistically significantly higher accuracy and AUC values (p<0.05 in Mann-Whitney U tests). The robustness of these findings is confirmed after controlling for heterogeneity among countries. Sensitivity analyses further reveal that both performance variables (e.g., Jensen's alpha, market return) and fundamental factors (e.g., fund size, manager expertise) have a significant impact on risk outcomes within these models. At the same time, machine learning methods exhibit a stronger ability to identify and quantify the importance of these variables compared to classical methods. The results highlight the practical advantage of adopting machine learning techniques for risk assessment and management in diverse international financial markets. Overall, the findings of this study reveal that employing machine learning models—especially Random Forest and Artificial Neural Networks—significantly improves the accuracy of ETF risk prediction and enables a more comprehensive identification of key risk factors compared to classical statistical approaches. These models demonstrate superior flexibility and the ability to capture complex, multidimensional data patterns, making them highly advantageous tools for financial risk management. The results suggest that integrating advanced machine learning techniques at both regional and international levels can enhance the responsiveness of investment systems to market changes, providing fund managers and investors with a more solid, data-driven basis for decision-making.