International Journal of Financial Technology and Global Risk Studies

Abstract PURPOSE: This study evaluates the ability of the Random Forest algorithm to predict the daily return of an equity investment fund managed by Charisma Asset Management, compares it with linear regression and a single decision tree as reference models, and identifies the most influential predictors of fund return.
DESIGN/METHODOLOGY/APPROACH: Daily data for the Karis (Sepehr Charisma) equity fund from Farvardin 1399 to Esfand 1403 (2020–2025) were cleaned by removing non-trading days and verified data-recording errors, resulting in 1,019 actual trading days. Fund-return, market-return, and asset-composition data were matched by date, and return-based features were constructed using only lagged information, leaving 989 observations for model estimation. Fund-specific and market variables were used to predict the total daily return. The models were trained using a chronological split, tuned with five-fold time-series cross-validation, and evaluated using RMSE, MAE, R², and directional accuracy.
FINDINGS: On the test set, linear regression achieved the highest predictive performance (R² = 0.721), whereas Random Forest produced comparable results (R² = 0.680) and outperformed the single decision tree. In five-fold time-series cross-validation, Random Forest achieved the highest mean R² and the lowest mean RMSE. Market return and short-term momentum variables were the dominant predictors. Excluding the contemporaneous market return reduced the R² of both models to approximately 0.28. Because no formal forecast-comparison tests were conducted, these comparisons are descriptive.
RESEARCH IMPLICATIONS: For asset managers and investors, daily fund returns are driven mainly by systematic market movements, so the information set matters more than algorithmic complexity. The single-fund design limits generalizability, the asset-allocation variables varied little over time, which may have reduced their predictive contribution, and macroeconomic predictors were not available at a daily frequency.
ORIGINALITY/VALUE: This study provides a case study of daily return prediction for a specific Iranian equity fund using Random Forest, with particular emphasis on performance variation across time-series validation folds and on the distinction between contemporaneous explanation and genuine forecasting.

Abstract PURPOSE: This study examines whether board independence affects corporate tax aggressiveness and whether it moderates the relationship between earnings management and tax aggressiveness in Iran, an emerging market in which listed firms benefit from statutory tax incentives.
DESIGN/METHODOLOGY/APPROACH: Using 1,000 firm-year observations from 125 non-financial firms listed on the Tehran Stock Exchange and Farabourse over 2013–2022, we estimate multivariate panel regressions with year fixed effects and heteroskedasticity-consistent standard errors, controlling for industry-level effective tax rates that reflect statutory exemptions. Tax aggressiveness is measured by book–tax differences, earnings management by discretionary accruals from the modified Jones model, and board independence by an indicator of an above-average proportion of independent directors. The models are re-estimated for large versus small firms and for firms with high versus low free float.
FINDINGS: Board independence is positively and significantly associated with tax aggressiveness in the full sample and among large firms. Earnings management is positively related to tax aggressiveness, and this relationship is stronger in firms with more independent boards. The direct effect of board independence is significant only in firms with below-average free float, where ownership is more concentrated, whereas its moderating effect is significant in firms with above-average free float.
RESEARCH IMPLICATIONS: In emerging markets with concentrated ownership and generous tax incentives, formally independent boards do not necessarily curb aggressive tax planning. Tax authorities and governance regulators should therefore look beyond board composition when assessing corporate tax risk.
ORIGINALITY/VALUE: The study provides new evidence from Iran, an under-researched setting in which statutory tax rates differ between listed and non-listed firms, and shows how board structure conditions the nexus between earnings management and tax aggressiveness.

Abstract PURPOSE: This study examines two dimensions of informational efficiency among Dow Jones Industrial Average (DJIA) constituents: the leakage of price-relevant information before scheduled corporate disclosures and the speed at which prices absorb newly released information. Quarterly earnings announcements serve as the information event. DESIGN/METHODOLOGY/APPROACH: Open, high, low, and closing prices for 26 DJIA constituents over 2010–2024 were obtained from Yahoo Finance, and announcement dates were identified from Form 8-K filings (Item 2.02) submitted to the U.S. Securities and Exchange Commission. Volatility, measured as the daily high–low range relative to the closing price, was examined over an eleven-day window around each announcement, yielding 1,568 events and 17,248 firm-day observations. Differences across event-window days were tested at the firm and pooled levels using one-way ANOVA and independent-samples t-tests, with effect sizes reported alongside p-values. FINDINGS: Volatility differs across the event window (F = 158.39, p < 0.0001, η² = 0.084), a pattern significant for all 26 firms, and peaks on the announcement day at roughly 60% above the pre-announcement baseline (Cohen’s d = 0.95). The elevation persists into the following trading day (d = 0.46, significant for 15 of 26 firms) before normalizing by day +2. Volatility in the two days preceding the announcement shows no economically meaningful difference (d = 0.13, significant for one firm), providing no support for systematic pre-disclosure leakage. RESEARCH IMPLICATIONS: The results support a qualified view of semi-strong-form efficiency: reactions are large and essentially leakage-free, but full price discovery takes slightly more than one trading session for most firms. They also show why effect sizes, not p-values alone, are needed to interpret large financial panels. ORIGINALITY/VALUE: The study jointly maps pre-disclosure leakage and post-disclosure adjustment speed using a single recurring event across a fifteen-year panel of DJIA constituents and explicitly separates statistical from economic significance.

Abstract PURPOSE: Political uncertainty strongly affects corporate performance and portfolio returns in emerging capital markets, yet validated political risk indicators have rarely been integrated into efficiency-based portfolio optimization. This study proposes a risk-adjusted data envelopment analysis (DEA)–Malmquist framework for portfolio selection in the Iranian capital market. DESIGN/METHODOLOGY/APPROACH: Political risk indicators were identified through a systematic literature review and validated by an eleven-member expert panel using the content validity ratio and content validity index. The validated indicators were then entered as additional inputs into an input-oriented super-efficiency DEA model, and dynamic performance was assessed with the Malmquist productivity index. The framework was applied to panel data for 106 firms listed on the Tehran Stock Exchange and Iran Fara Bourse over 2009–2023, and the resulting efficiency and productivity measures were used to construct a twenty-stock portfolio. FINDINGS: Risk-adjusted super-efficiency scores differ substantially across firms and industries, and productivity change varies widely, driven by both technical efficiency change and technological change. The selected twenty-stock portfolio is weighted toward pharmaceutical and automotive-parts firms that combine relatively high efficiency and productivity growth with lower exposure to political shocks. RESEARCH IMPLICATIONS: Treating political risk as an explicit component of efficiency measurement, rather than as an external factor, offers investors, portfolio managers, and policymakers a structured decision-support tool for building more resilient portfolios in politically uncertain environments. ORIGINALITY/VALUE: The study combines expert-validated political risk indicators, super-efficiency DEA, and the Malmquist productivity index within a single portfolio-selection framework for an emerging market exposed to sanctions and policy uncertainty.

Abstract PURPOSE: This study examines whether corporate sustainability performance moderates the relationship between economic policy uncertainty and the investment of firms listed on the Tehran Stock Exchange.
DESIGN/METHODOLOGY/APPROACH: The study is applied in purpose and correlational, ex post facto in design. After applying the sample-selection criteria, 156 firms were analyzed over 2015–2024, yielding a balanced panel of 1,560 firm-year observations. Data were collected from financial statements, board of directors’ reports, and other public disclosures. Economic policy uncertainty is constructed from four macroeconomic indicators using principal component analysis, sustainability performance is measured by content analysis of a 56-item environmental, social, and governance disclosure checklist, and the hypotheses are tested with fixed-effects panel regressions using heteroskedasticity-robust standard errors.
FINDINGS: Economic policy uncertainty has a negative and statistically significant effect on corporate investment, indicating that greater ambiguity in economic policy reduces firms’ willingness to undertake new investment. The interaction between economic policy uncertainty and sustainability performance is positive and significant, indicating that sustainability performance weakens this negative relationship: firms with stronger environmental, social, and governance performance experience a smaller decline in investment when policy uncertainty rises.
RESEARCH IMPLICATIONS: Sustainability performance can serve as a mechanism that strengthens corporate resilience and mitigates the adverse effects of economic instability on investment, which is relevant to managers, investors, and policymakers in uncertain emerging-market environments.
ORIGINALITY/VALUE: The study provides evidence from Iran, a market characterized by persistent policy uncertainty, on the moderating role of sustainability performance in the uncertainty–investment relationship, a link that has received limited attention in prior research.

Abstract PURPOSE: This study examines whether managerial overinvestment is associated with corporate risk-taking, whether financial constraints alter this relationship in an emerging, bank-dependent capital market, and whether corporate risk-taking is associated with firm value. DESIGN/METHODOLOGY/APPROACH: We use a balanced panel of 94 non-financial firms listed on the Tehran Stock Exchange over fourteen fiscal years (1389–1402 in the Iranian calendar, corresponding to 2010/11–2023/24), yielding 1,316 firm-year observations. Managerial overinvestment is measured as the positive component of firms’ investment deviation, corporate risk-taking as the three-year rolling standard deviation of annual stock returns, financial constraints as a standardized liquidity-based measure (the negative logarithm of one plus the current ratio), and firm value as Tobin’s Q. Two-way firm and year fixed-effects models with firm-clustered standard errors are estimated using one-year-lagged explanatory variables. FINDINGS: In the risk-taking model, the coefficient on managerial overinvestment is negative but statistically insignificant, and neither the financial-constraint measure nor its interaction with overinvestment is significant. In the firm-value model, lagged corporate risk-taking is positively associated with Tobin’s Q, whereas managerial overinvestment is negatively associated with firm value. RESEARCH IMPLICATIONS: Managerial investment behavior and the financing environment should be considered jointly when examining corporate risk-taking and valuation in emerging markets. The market consequences of excessive investment may be visible in firm value even when the direct risk-taking channel is not statistically strong. ORIGINALITY/VALUE: The study provides an integrated panel analysis that links managerial overinvestment, financial constraints, market-based corporate risk-taking, and firm value for firms listed on the Tehran Stock Exchange.