دانشگاه اصفهان مدیریت دارایی و تامین مالی 2383-1189 14 4 2026 12 22 55 55 30875 FA Journal Article 2026 09 29 https://amf.ui.ac.ir/article_30875_0ff71d92919f850e436c5ebf7df8f8e0.pdf

دانشگاه اصفهان مدیریت دارایی و تامین مالی 2383-1189 14 4 2026 12 22 The Impact of Trade Friction on the Financialization of Firms Considering Management Characteristics تأثیر اصطکاک تجاری بر مالی‌سازی شرکت‌ها با در نظر گرفتن ویژگی‌های مدیریتی 1 22 30042 10.22108/amf.2025.144797.1973 FA نگین محمدقلی زاد کارشناسی ارشد، گروه حسابداری، دانشکدۀ اقتصاد و مدیریت، دانشگاه ارومیه، ارومیه، ایران علی آشتاب دانشیار، گروه حسابداری، دانشکدۀ اقتصاد و مدیریت، دانشگاه ارومیه، ارومیه، ایران فرزاد غیور استادیار، گروه حسابداری، دانشکدۀ اقتصاد و مدیریت، دانشگاه ارومیه، ارومیه، ایران Journal Article 2025 04 09 This study investigates the impact of trade friction on corporate financialization, with a specific focus on the moderating role of managerial self-interest and the mediating role of managerial short-sightedness. Using a sample of 103 non-financial firms listed on the Tehran Stock Exchange (TSE) and the Iran Fara Bourse (IFB) from 2013 to 2023, selected via a systematic elimination method, the research employs multiple linear regression and the Prais–Winsten estimation technique. The findings reveal that trade friction exerts a significant positive effect on the level of corporate financialization. Moreover, managerial self-interest is found to positively moderate this relationship, while managerial short-sightedness serves as a significant mediating mechanism. These results imply that trade frictions can exacerbate managerial myopia, prompting a shift towards short-term financial investments. Departing from prior literature that has centered on managerial traits or market-level responses, this study provides novel insights by delineating the critical roles of managerial self-interest and short-sightedness in the nexus between trade friction and corporate financialization. Keywords: Corporate Financialization, Managerial Self-interest, Managerial Short-sightedness, Trade Friction JEL: G32, M12, F14 Introduction In the contemporary global economy, nations largely embrace free trade, facilitated by bilateral and multilateral agreements, to foster economic growth and enhance profitability by reducing tariff and non-tariff barriers (Liu et al., 2023). Despite this trend, trade friction remains an inherent and complex feature of the international trading system, posing significant challenges to firm performance and strategic decision-making (Guo et al., 2024). Prominent instances, such as the Sino-American trade dispute (Huang et al., 2023) and the sustained economic sanctions on Iran (Razm-Ahang, 2019), illustrate how such frictions can disrupt corporate operations. These conditions often manifest as increased operational costs, constrained market access, and diminished returns on real investments, which can, in turn, incentivize a corporate shift towards financial asset allocation—a phenomenon known as corporate financialization (Jin et al., 2022). The role of corporate leadership in this dynamic is critical. Managers, often driven by job security or short-term incentives, may make strategic choices that prioritize immediate gains over the firm's long-term value, a manifestation of managerial self-interest (Hou et al., 2021). This raises a pivotal question: through what mechanisms do external trade shocks translate into internal financialization strategies? Against this backdrop, this study seeks to address a central research question: How does trade friction influence corporate financialization, and what roles do managerial short-sightedness and managerial self-interest play in this relationship? We posit managerial short-sightedness as a mediating mechanism and managerial self-interest as a moderating condition. Specifically, the following hypotheses are proposed: H1: Trade friction has a significant positive effect on corporate financialization. H2: Managerial self-interest strengthens the positive relationship between trade friction and corporate financialization. H3: Managerial short-sightedness mediates the relationship between trade friction and corporate financialization. Materials & Methods The sample of this study comprises 103 companies listed on the Tehran Stock Exchange (TSE) and Iran Fara Bourse (IFB) from 2013 to 2023. The sample selected through a systematic elimination process based on the following criteria: inclusion of firms with export sales; availability of complete and reliable financial information for extracting research variables; a fiscal year ending on March 20 to ensure comparability; and no change in fiscal year during the study period. Companies in brokerage, investment, leasing, banking, and insurance industries were excluded due to their distinct operational nature. Financial data were sourced from Rahavard Novin software and initially processed in Microsoft Excel. The final analyses were performed using EViews, Stata, and AMOS. The Sobel test was employed to examine the mediating effect. Findings The findings indicate that trade friction exerts a direct and significant positive effect on corporate financialization. This suggests that heightened trade restrictions prompt firms to expand their financial activities while diverting focus from real investment. Furthermore, managerial self-interest positively moderates this relationship; specifically, in environments characterized by trade friction, managers exhibiting higher self-interest demonstrate a greater propensity for short-term financial decision-making. Additionally, managerial short-sightedness serves as a partial mediator, channeling a portion of the effect of trade friction on financialization through a short-term managerial orientation. Complementary analyses using Tobit regression corroborate the significant positive impact of trade friction on financialization, confirming that these results are robust across company types (i.e., listed on TSE versus IFB). Discussion and Conclusion In conclusion, this study demonstrates that trade friction, by heightening environmental risks and imposing operational constraints, exerts a significant influence on corporate financial decision-making. The findings confirm the research hypotheses, indicating that these external pressures lead to an expansion of financial activities at the expense of real investment. Moreover, managerial self-interest acts as a positive moderator, intensifying this relationship as self-interested managers demonstrate a greater propensity for short-term decisions amidst trade disputes. The results also identify managerial short-sightedness as a partial mediator, channeling a portion of the effect of trade friction on financialization through a short-term managerial orientation. The robustness of these findings across both the Tehran Stock Exchange (TSE) and Iran Fara Bourse (IFB) underscores that the influence of such environmental pressures is pervasive, transcending specific listing venues. These insights collectively emphasize the necessity of integrating environmental, institutional, and managerial factors in models of corporate financialization. From a practical standpoint, they underscore the critical role of robust corporate governance and regulatory oversight in mitigating the short-termism amplified by managerial self-interest. While this study is subject to limitations—such as the unavailability of disaggregated data on domestic versus export profits and a sample confined to listed companies—it opens several avenues for future inquiry. Subsequent research could investigate sectoral variations, incorporate broader macroeconomic variables, and probe deeper into managerial psychological traits. Such efforts would yield a more nuanced understanding of the nexus between trade friction and financialization and provide actionable guidance for refining corporate financial strategy. هدف پژوهش، بررسی تأثیر اصطکاک تجاری بر مالی‌سازی شرکت‌ها و تبیین نقش تعدیل‌گر فرصت‌طلبی و میانجی کوته‌بینی مدیران است. به‌منظور آزمون فرضیه‌ها، نمونه‌ای شامل ۱۰۳ شرکت بورسی و فرابورسی ایران طی دورۀ ۱۳۹۲ تا ۱۴۰۲ به روش حذف سیستماتیک انتخاب و داده‌ها ازطریق اسنادکاوی گردآوری شد. تحلیل فرضیه‌ها با استفاده از رگرسیون خطی چندگانه و رویکرد پرایس _ وینستون صورت گرفت. یافته‌ها نشان داد اصطکاک تجاری تأثیر مستقیم و معناداری بر سطح مالی‌سازی شرکت‌ها دارد؛ افزون بر این، فرصت‌طلبی مدیران رابطۀ میان اصطکاک تجاری و مالی‌سازی را تقویت می‌کند و کوته‌بینی مدیران نیز به‌طورمستقیم موجب افزایش مالی‌سازی می‌شود. نتایج حاکی‌ازآن است که اصطکاک تجاری می‌تواند رفتارهای مالی و تصمیم‌گیری‌های کوتاه‌مدت مدیران را تشدید کند. باتوجه‌به اینکه پژوهش‌های پیشین عمدتاً بر تأثیر ویژگی‌های شخصیتی مدیران بر تصمیم‌گیری‌های مالی، واکنش بازار به تغییرات محیطی و ارتباط میان مالی‌سازی و سرمایه‌گذاری واقعی متمرکز بوده‌اند، این پژوهش به‌طور منحصربه‌فرد اثر ویژگی‌های مدیریتی را بر رابطۀ میان اصطکاک تجاری و مالی‌سازی شرکت‌ها بررسی می‌کند و نقش تعدیلی فرصت‌طلبی و میانجی کوته‌بینی مدیران را موردتوجه قرار می‌دهد.

https://amf.ui.ac.ir/article_30042_f86486a2df2ad14edaf356392b6fc28a.pdf

دانشگاه اصفهان مدیریت دارایی و تامین مالی 2383-1189 14 4 2026 12 22 stock selection by using hierarchical risk parity method and minimum spanning tree based on correlation coefficients matrix in the 50 most active companies of Tehran Stock Exchange انتخاب سهام با استفاده از رویکرد برابری ریسک سلسله‌مراتبی و درخت پوشای کمینه مبتنی بر ماتریس ضرایب همبستگی در 50 شرکت فعال‌تر بورس اوراق بهادار تهران 23 46 30093 10.22108/amf.2025.143014.1930 FA سعید فلاح پور دانشیار، گروه مهندسی مالی، دانشکدۀ حسابداری و علوم مالی، دانشکدگان مدیریت، دانشگاه تهران، تهران، ایران علی نمکی دانشیار، گروه مهندسی مالی، دانشکدۀ حسابداری و علوم مالی، دانشکدگان مدیریت، دانشگاه تهران، تهران، ایران 0000-0003-4167-6472 رضا فضلی کارشناس ارشد، دانشکدۀ حسابداری و علوم مالی، دانشکدگان مدیریت، دانشگاه تهران، تهران، ایران Journal Article 2024 10 13 Portfolio optimization represents a central challenge in financial investment. This study evaluates the performance of a proposed stock selection model for the Tehran Stock Exchange, comparing its outcomes to both the market index and the Markowitz model using statistical tests. Portfolios were constructed by applying the Hierarchical Risk Parity (HRP) method combined with marginal asset selection, utilizing two distinct correlation matrices. These portfolios were rebalanced semiannually based on updated correlation coefficients and the composition of the Top 50 Active Companies Index. The results demonstrate that the HRP approach with asset selection generally outperforms both the index and the Markowitz model in terms of portfolio performance, a finding consistent across various market conditions, including recessions and booms. Statistical tests confirm the significant superiority of this method over the Markowitz approach. Furthermore, this research achieved effective diversification within the Tehran Stock Exchange using fewer assets than other methods. The primary innovation of this work lies in the application of two distinct correlation matrices and the implementation of two novel methodologies for asset weighting and selection, offering practical insights for both individual and institutional investors. Keywords: Portfolio Optimization, Hierarchical Risk Parity, Minimum Spanning Tree, Asset Selection, Marginal Sssets JEL Classification: C61, G11, G32 Introduction The process of selecting financial assets and constructing an investment portfolio has long been characterized by uncertainty. Portfolio management—which entails the analysis, selection, and ongoing maintenance of a collection of investments—is inherently complex and often lacks a formalized structure. Capital markets allow investors to allocate surplus capital across various assets to generate profit. A primary objective of investment is to distribute capital among a set of assets in a manner that maximizes expected return while minimizing associated risk (Namaki & Kafi Mousavi, 2023). Investors tend to prefer assets or asset combinations that offer the highest expected return for a given level of risk. Consequently, understanding the future price behavior of assets, the factors that influence them, and their associated risks is essential (Noorahmadi & Sadeghi, 2023). The stock market, as a central investment venue, has attracted significant attention, yet the selection of an optimal stock portfolio remains a complex challenge influenced by numerous variables (Tavakoli et al., 2013). Accurately assessing portfolio risk requires a clear understanding of the dynamic relationships among assets. While correlation matrices are commonly used for this purpose, they often contain noise due to market instability. Techniques such as Minimum Spanning Trees (MST) and Planar Maximally Filtered Graphs (PMFG) can help filter this noise and clarify underlying asset linkages (Pozzi et al., 2013). Financial markets also exhibit inherent hierarchical structures, with interconnected industries and sectors. Hierarchical Risk Parity (HRP)—the core methodological framework of this study—capitalizes on such structures to achieve improved diversification and risk control. By integrating HRP with MST and employing two distinct correlation matrices, this research seeks to construct efficient portfolios within the Tehran Stock Exchange, balancing theoretical rigor with practical applicability. Materials and Methods The data for this study were sourced from the historical trading records of the Tehran Stock Exchange (TSE), with a specific focus on its 50 most active companies. The analysis covers the period from 2016 to early 2023. All data processing and model implementation were performed using Python. Initially, the logarithmic daily returns for the selected stocks were computed for each six-month interval. These returns were then used to derive covariance and correlation matrices. Two distinct types of correlation matrices were employed: a Full Cross-Correlation (FC) matrix and a Global Motion Subtracted Correlation (GMSC) matrix. The GMSC was obtained by filtering out the market-wide component based on the eigenvalue distribution defined by the Marchenko–Pastur theorem. The Hierarchical Risk Parity (HRP) method was subsequently applied for portfolio construction. The correlation matrices were first converted into metric distance matrices, after which Minimum Spanning Trees (MST) were generated using Kruskal’s algorithm. The HRP algorithm itself follows a three-step procedure: (1) hierarchical clustering to group assets with similar return profiles, (2) quasi-diagonalization of the covariance matrix to order correlated assets contiguously, and (3) recursive bisection for top-down capital allocation, wherein riskier clusters are assigned proportionally lower weights. To improve diversification and streamline the portfolio, a marginal asset selection process was implemented using modified network centrality and periphery metrics—specifically, degree, betweenness, closeness, eccentricity, and eigenvector centrality. Assets identified as peripheral based on a composite of these centrality measures were selected for inclusion. Portfolios of varying sizes (comprising 3, 5, 10, 20, and 30 assets) were formed and rebalanced on a semiannual basis. The performance of the portfolios constructed using the HRP methodology was evaluated against two benchmarks: the TSE Top 50 Index and a classical Markowitz mean–variance optimization model. The Markowitz model was constrained to non-negative weights in accordance with the short-selling restrictions present in the Iranian capital market. Findings The analysis was conducted using adjusted price data for the 50 most active companies on the Tehran Stock Exchange from July 2016 to January 2023. From logarithmic and normalized returns, two distinct correlation matrices were constructed: a Full Cross-Correlation (FC) matrix and a Global Motion-Subtracted Correlation (GMSC) matrix. These matrices were used to build Minimum Spanning Trees (MSTs), identify marginal assets, and implement the Hierarchical Risk Parity (HRP) algorithm, which involved hierarchical clustering, quasi-diagonalization, and recursive bisection. Eight distinct portfolio strategies were evaluated based on the number of assets (5, 10, 25, 50) and the type of correlation matrix used. The results indicate that HRP-based portfolios consistently outperformed both the Top 50 Index and the Markowitz model across several key metrics, including cumulative returns, annualized returns, Sharpe ratios, and drawdown reduction. For instance, the GMSC-HRP (10 assets) and FC-HRP (5 assets) strategies achieved cumulative returns of 2966% and 2625%, respectively, compared to the index's return of 2034%. The Wilcoxon signed-rank test confirmed the statistically significant superiority of six out of the eight HRP-based portfolios at the 10% significance level. A regime-based analysis further contextualizes these results. HRP portfolios delivered performance comparable to the index during stable periods, significantly outperformed it during the bull market (2017–2020), and demonstrated a marked ability to mitigate losses during the subsequent bear market (2021–2022). Notably, FC-HRP models were found to be more effective for smaller portfolio sizes, making them suitable for individual investors, whereas GMSC-HRP models performed better with larger portfolios, aligning with the needs of institutional investors. In summary, the HRP approach, combined with MST-based marginal asset selection, provided robust diversification, superior risk-adjusted returns, and demonstrated resilience across varying market conditions. Discussion and Conclusion The findings demonstrate that the Hierarchical Risk Parity (HRP) approach, combined with asset selection, generally outperformed the Top 50 Index, resulting in lower portfolio standard deviation and superior risk-adjusted returns, as evidenced by higher Sharpe ratios. Both correlation inputs—the Full Cross-Correlation (FC) and the Global Motion Subtracted Correlation (GMSC) matrices—were found to be effective within the HRP framework. A principal contribution of this study is the novel simultaneous application of the GMSC matrix and the integration of HRP asset weighting with MST-based marginal asset selection, specifically for the Tehran Stock Exchange (TSE). The results suggest a distinct advantage based on portfolio size: the FC matrix yielded superior performance for smaller portfolios (e.g., 5 assets), whereas the GMSC matrix proved more effective for larger portfolios. Consequently, FC-based HRP models are recommended for individual investors with limited capital, while GMSC-based strategies appear better suited for institutional investors. HRP-based portfolios delivered particularly strong results during the bull market (2017–2020) and demonstrated notable resilience during the subsequent downturn beginning in August 2020, effectively mitigating losses. Furthermore, the HRP weighting method, even without asset selection, improved the performance of the full 50-asset portfolio compared to simple index weighting. The use of marginal asset selection via Minimum Spanning Tree (MST) facilitates efficient diversification with a smaller asset count, reducing associated trading costs while preserving portfolio efficiency. Future research could enhance the model by integrating HRP with machine learning techniques or exploring advanced graph-based market structures to improve predictive accuracy and interpretability. Extending this methodology to other asset classes in the Iranian market, such as bonds, gold ETFs, and derivatives, would further test its capacity for risk reduction and return enhancement. مسئلۀ بهینه‌سازی سبد دارایی یکی از چالش‌های اساسی در حوزۀ سرمایه‌گذاری مالی است. هدف این پژوهش، ارزیابی عملکرد مدل ارائه‌شده برای انتخاب سهام در بورس اوراق بهادار تهران و مقایسۀ آن با شاخص و رویکرد مارکوویتز براساس آزمون‌های آماری است. در پژوهش حاضر، با استفاده از روش وزن‌دهی برابری ریسک سلسله‌مراتبی و انتخاب دارایی‌های حاشیه‌ای، سبدهای سهام ساخته شده‌ است. این سبدها در دو حالت مختلف براساس ماتریس‌های همبستگی متفاوت تشکیل شده و سپس هر شش ماه یک‌بار براساس ضرایب همبستگی و ترکیب شرکت‌های عضو شاخص ۵۰ شرکت فعال‌تر، بازنگری و وزن‌دهی مجدد شده‌ است. در ادامه، عملکرد این سبدها با شاخص ۵۰ شرکت فعال‌تر و رویکرد مارکوویتز مقایسه گردیده است. نتایج نشان می‌دهد که رویکرد ریسک سلسله‌مراتبی با انتخاب دارایی توانسته است در بیشتر موارد عملکرد سبد سهام را براساس شاخص‌های ارزیابی در مقایسه با شاخص و رویکرد مارکوویتز بهبود دهد. نتایج آزمون‌های آماری نیز برتری معنادار این روش را در مقایسه با رویکرد مارکوویتز تأیید می‌کند. افزون بر این، پژوهش حاضر توانسته است با انتخاب بهینۀ دارایی و ساخت سبدهایی با تعداد دارایی کمتر در مقایسه باروش‌های مشابه، به تنوع‌بخشی کارآمد در بورس اوراق بهادار تهران دست یابد. نوآوری اصلی این پژوهش در استفادۀ هم‌زمان از دو ماتریس همبستگی متفاوت به‌عنوان ورودی و به‌کارگیری دو روش نوین برای وزن‌دهی و انتخاب دارایی در بازار سهام تهران است؛ به‌گونه‌ای‌که نتایج آن می‌تواند برای سرمایه‌گذاران شخصی و نهادی در استفاده از ماتریس‌های همبستگی مختلف کاربرد داشته باشد.

https://amf.ui.ac.ir/article_30093_9b9c03f14981d8dcab4fce6f04bec412.pdf

دانشگاه اصفهان مدیریت دارایی و تامین مالی 2383-1189 14 4 2026 12 22 Portfolio Optimization Using Quantitative Value Allocation Method in Iran's Capital Market بهینه‌سازی سبد سهام با روش تخصیص ارزش کمّی در بازار سرمایۀ ایران 47 68 30156 10.22108/amf.2025.140404.1979 FA میثم دعائی گروه مدیریت مالی، دانشگاه آزاد اسلامی واحد اسفراین، اسفراین، ایران Journal Article 2025 05 04 This study proposes and implements a two-phase portfolio optimization model in Tehran Stock Eschange (TSE) and Iran Farabourse Company, integrating a quantitative value assessment with a multi-objective optimization framework. The first phase involves a fundamental valuation of constituent companies, while the second phase constructs an optimal portfolio using a multi-objective mathematical model. The epsilon-constraint method was employed to solve the model, utilizing financial data sourced from the Codal database. Empirical results demonstrate the model's efficacy in supporting investment decision-making. Portfolios formed through this integrated approach, which systematically incorporates both fundamental and technical analysis, significantly outperformed randomly selected portfolios. Furthermore, the model successfully accommodated diverse investor preferences within the asset selection process. By developing a structured quantitative framework grounded in a defined value function and multi-objective optimization, this research provides a precise and adaptable tool for optimal asset allocation in TSE, facilitating the simultaneous application of fundamental and technical criteria in portfolio construction. Keywords: Tehran Stock Exchange, Iran Farabourse Company, Portfolio Optimization, Quantitative Value Allocation. JEL: G11, C61, C44, C58, G12. Introduction This study examines the application of a quantitative value allocation (QVA) framework to portfolio optimization in the TSE and Iran Farabourse Company. The proposed framework integrates principles of fundamental and technical analysis into a multi-objective optimization structure, aiming to address limitations inherent in classical portfolio models. Traditional approaches, most notably the mean–variance model, often rely on simplified assumptions—such as perfect asset divisibility, negligible transaction costs, and static investor preferences—that seldom align with the realities of emerging markets. In contexts such as Iran’s capital market, challenges including varying disclosure quality, liquidity constraints, and pronounced market frictions further complicate the direct application of conventional models. To bridge this gap, the present study introduces a more realistic portfolio construction model that accounts for multi-period progression, firm-level fundamental scoring, interdependencies in risk factors, and heterogeneous investor utility functions. The study is guided by the following central research question: Can a hybrid, value-driven quantitative methodology yield portfolio performance superior to random selection, and does the integration of fundamental and technical signals contribute to a more robust and consistent investment strategy under Iran’s specific market conditions? Methods & Materials This study employs a two-phase mathematical modeling framework. The first phase develops a quantitative value function to screen companies based on six fundamental dimensions: liquidity, efficiency, leverage, profitability, market valuation metrics, and systematic risk. Each indicator is converted into a unit-free score using adjustable preference thresholds, categorizing performance into acceptable, neutral, or penalty zones; only stocks with a positive aggregate score advance to the subsequent stage. The second phase formulates a three-objective optimization model designed to maximize the portfolio's temporal progression, maximize its time-weighted average value, and minimize the covariance among selected assets. The model incorporates constraints on the number of assets, minimum and maximum investment thresholds, and binary inclusion decisions. The ε-constraint method is utilized to generate the Pareto-efficient frontier, selected for its efficacy in navigating non-convex, multi-objective search spaces. The empirical analysis utilizes financial data from 420 companies listed on the Tehran Stock Exchange and Iran Fara Bourse between 2017 and 2021, sourced from Codal, Fipiran, and official market databases. For comparative performance evaluation, the proposed model is benchmarked against portfolios constructed via three alternative approaches: random selection, low-beta selection, and a strategy based on technical indicators (MFI, RSI, SMA, and MACD), with each portfolio comprising seven assets. Findings he value-based screening process successfully identifies a subset of firms exhibiting robust fundamentals across key industries, including basic metals, pharmaceuticals, chemicals, cement, and energy. These firms, characterized by superior composite value scores, are subsequently integrated into the multi-objective optimization model. The solution generated via the ε-constraint method yields an optimized portfolio encompassing assets from over twenty-five industries, effectively balancing sectoral exposure while achieving high aggregate value and maintaining low inter-asset covariance. This allocation not only adheres to defined investor constraints but also results in stable and interpretable portfolio weights. Comparative backtesting reveals that portfolios constructed using the proposed Quantitative Value Allocation (QVA) framework consistently outperform randomly selected portfolios in terms of both absolute returns and performance consistency. While beta-based diversification strategies improve risk-adjusted returns relative to random portfolios, they generally underperform the optimized value-based model. Portfolios formed exclusively on technical signals (MFI, RSI, SMA, MACD) demonstrate periods of high returns but are accompanied by significantly elevated volatility. Overall, the integrated hybrid approach delivers the most stable and favorable performance profile, underscoring the persistent explanatory power of fundamental valuation as a core performance driver even within volatile and informationally constrained market environments. Discussion and Conclusion This study demonstrates that a quantitative, value-centric, multi-objective portfolio optimization framework presents significant empirical and theoretical advantages over heuristic or discretionary portfolio construction methods. By integrating a fundamental valuation screen with a formal multi-objective model and augmenting this with technical signals, the proposed approach effectively synthesizes firm-level structural attributes with market-driven price dynamics. The findings substantiate contemporary theoretical arguments advocating for the fusion of economic fundamentals with quantitative techniques, aligning with the growing literature on hybrid strategies for emerging markets. From a practical standpoint, the model offers a structured, actionable tool for investors, underscoring that systematic value-based selection can enhance long-term performance and improve risk management relative to random or single-factor strategies. The study acknowledges inherent limitations, including potential data quality constraints, the static nature of the fundamental scoring, and the model's omission of exogenous macroeconomic shocks. Future research should aim to extend this framework by introducing dynamic preference mechanisms, stress-testing its performance under extreme volatility, or integrating robust or fuzzy optimization techniques to better account for parameter uncertainty. In conclusion, this research contributes a flexible and empirically validated framework that refines portfolio selection practices within the Iranian capital market while providing a foundational platform for subsequent methodological innovation. هدف اصلی پژوهش، طراحی و پیاده‌سازی یک مدل بهینه‌سازی سبد سهام با رویکرد تخصیص ارزش کمّی در بستر بازار سرمایۀ ایران است. این پژوهش در دو فاز شامل ارزیابی کمّی ارزش شرکت‌ها و بهینه‌سازی سبد سرمایه‌گذاری با اهداف چندگانه تدوین شد. داده‌ها از سایت کدال استخراج و برای حل مدل بهینه‌سازی چندهدفه از الگوریتم اپسیلون استفاده شده است. نتایج، کارایی رویکرد پیشنهادی در ارتقای تصمیم‌گیری سرمایه‌گذاران را تأیید می‌کند. نتایج نشان داد که سبدهای تشکیل‌شده براساس تحلیل بنیادی و تکنیکال در مقایسه با انتخاب‌های تصادفی بازدهی بیشتری داشتند و مدل ارائه‌شده توانست ترجیحات متنوع سرمایه‌گذاران را در انتخاب بهینۀ دارایی‌ها به‌طور مؤثری لحاظ کند. این پژوهش با توسعۀ یک چارچوب کمّی دومرحله‌ای مبتنی بر تابع ارزش و بهینه‌سازی چندهدفه، مدلی دقیق و منعطف برای تخصیص بهینۀ دارایی‌ها در بازار سرمایۀ ایران ارائه کرده است که امکان لحاظ هم‌زمان تحلیل بنیادی و تکنیکال را در فرایند انتخاب سبد سهام فراهم می‌آورد.

https://amf.ui.ac.ir/article_30156_22a29f2babe7881ae12b44fe7ec59dbb.pdf

دانشگاه اصفهان مدیریت دارایی و تامین مالی 2383-1189 14 4 2026 12 22 Investor Sentiment and the Momentum of Excess Stock Returns تحلیل تأثیر احساسات سرمایه‌گذار بر روند حرکت بازدۀ مازاد سهام 69 90 30112 10.22108/amf.2025.146733.2013 FA امین حاجیان نژاد استادیار، گروه حسابداری، دانشکدۀ علوم اداری و اقتصاد، دانشگاه اصفهان، اصفهان، ایران علیرضا رهروی دستجردی استادیار، گروه حسابداری، دانشکدۀ علوم اداری و اقتصاد، دانشگاه اصفهان، اصفهان، ایران 0000-0001-6874-8398 امیرحسین خداپرست دانشجوی دکتری، گروه حسابداری، دانشکدۀ علوم اداری و اقتصاد، دانشگاه اصفهان، اصفهان، ایران Journal Article 2025 09 19 The behavioral finance perspective challenges the Efficient Market Hypothesis by asserting that investor decision-making is not driven solely by rationality and profit maximization. Instead, behavioral biases, such as investor sentiment, significantly influence investment decisions and, consequently, stock prices and returns. Accordingly, this study investigates the impact of investor sentiment on the momentum of excess stock returns in both the short and long term within the Tehran Stock Exchange. A screening method was employed to select a sample of 169 listed firms. These firms were analyzed using multivariate regression models with panel data from 2011 to 2022 for the first hypothesis and from 2011 to 2020 for the second and third hypotheses, controlling for year and industry effects. The findings indicate that investor sentiment positively affects the momentum of excess returns in the short term but exerts a negative impact in the long term. Furthermore, the results suggest that investor sentiment has a stronger influence on the momentum of excess returns for smaller firms than for larger firms over the long term. Keywords: Investor Sentiment, Momentum, Behavioral Finance Approach, Excess Stock Returns JEL classification: G41, G12, C23, E44 Introduction Behavioral finance challenges the Efficient Market Hypothesis by arguing that investors’ decisions are not driven solely by rational analysis (Mehrani et al., 2023) but are also influenced by psychological factors—most notably investor sentiment—that can distort stock prices and returns (De Long et al., 1990). Accordingly, this study investigates the impact of investor sentiment on the momentum of excess stock returns in both the short and long term, and explores how this effect varies with firm size in the Tehran Stock Exchange, a developing market (Romoozi et al., 2024; Talebzadeh & Sadeghi, 2020) characterized by limited arbitrage opportunities, restrictions on foreign investment, and short-selling constraints (Han & Li, 2017). These market frictions limit rational traders’ ability to quickly correct sentiment-driven mispricing, suggesting that investor sentiment positively affects short-term excess return momentum (H1). Over longer horizons, accumulated deviations from fundamental values trigger arbitrage activity, gradually correcting prices, so investor sentiment is expected to negatively affect long-term excess return momentum (H2). Additionally, smaller firms are harder to value and more prone to speculative trading, making them more sensitive to sentiment. Thus, investor sentiment’s effect on long-term excess return momentum is stronger for small firms than for large firms (H3). By testing these hypotheses, the study contributes to behavioral finance literature and provides insights for investors seeking to identify sentiment-driven return patterns in emerging markets. Materials & Methods Using a systematic screening procedure, a final sample of 169 non-financial firms listed on the Tehran Stock Exchange (TSE) was selected. The hypotheses were tested through multivariate panel-data regressions, controlling for year and industry effects. The analysis period spans 2011–2022 for the first hypothesis and 2011–2020 for the second and third hypotheses. The extended period for the first hypothesis reflects the requirements of the long-term excess-return momentum measure, which is based on 36-month forward returns, whereas short-term momentum relies on 12-month forward returns. Accordingly, forward returns from 2021–2023 were incorporated as appropriate. The final dataset includes 24,336 firm-month observations for short-term tests and 20,280 firm-month observations for long-term tests. The empirical model employed in this study is adapted from Han & Li (2017). Excess-return momentum was calculated using cumulative excess returns, defined as realized returns minus the risk-free rate. Investor sentiment (S) was measured using a composite index constructed through principal component analysis (PCA), following Hajiannejad (2023), Tohidi (2020), Ferreira et al., (2021), Khan & Ahmad (2019), Ling et al., (2010), and Baker & Wurgler (2006, 2007), while macroeconomic variables (Z) were included as control variables. Findings The results show that investor sentiment significantly influences excess return momentum across different time horizons and firm sizes. Descriptive statistics indicate that average investor sentiment was slightly positive over the study period, while cumulative excess returns exhibited variation across both short- and long-term horizons. Panel regressions—estimated using GLS with cross-sectional weights and White period–clustered covariance to address heteroskedasticity and serial correlation—reveal systematic patterns. In the short term, investor sentiment has a positive and statistically significant effect on excess return momentum, confirming Hypothesis 1 at the 1% level. In the long term, however, the effect becomes negative and significant, supporting Hypothesis 2. This shift in sign reflects a clear mean-reversion pattern, whereby return gradually reverse toward their fundamental value as the investment horizon lengthens. Separate estimations for large and small firms show that the long-term coefficient of investor sentiment is negative for both groups, but considerably larger in absolute value for small firms. A Z-test confirms that the long-term influence of sentiment on excess return momentum is significantly stronger for small firms than for large firms at the 1% level, thereby supporting Hypothesis 3. Overall, all three hypotheses are validated at the 99% confidence level. Discussion & Conclusion Short-term expectations of significant gains or losses drive retail and sentiment-driven investors toward aggressive buying or selling. Information asymmetry and structural market frictions amplify these fluctuations and slow price correction, generating momentum that causes stocks to continue upward or downward trends. Consequently, investor sentiment exerts a positive effect on short-term excess return momentum, consistent with Han & Li (2017) and Seok et al., (2019). Over the long run, as prices deviate from intrinsic values, rational and analysis-driven investors are better positioned and increasingly inclined to engage in corrective trading. These actions reduce sentiment pressures and allow the market to gradually revert toward fundamental equilibrium. The effect is particularly pronounced for smaller firms with limited analyst coverage, lower liquidity, and subjective valuation. These results are consistent with Baker et al., (2012) and Baker & Wurgler (2006, 2007). These findings suggest that short-term traders may benefit from periods of elevated positive sentiment, whereas long-term investors should prioritize fundamental analysis and avoid decisions driven solely by sentiment. For smaller firms, prudent decision-making and enhanced disclosure are essential. Regulators and asset managers can mitigate sentiment-induced volatility by improving transparency, expanding analytical coverage, and integrating sentiment indicators into risk management. The study’s main limitations include reliance on a single sentiment index, potential influence of uncontrolled external factors, and constraints from sample screening. Future research could employ alternative sentiment measures, include additional macro-level controls, and examine whether effects vary across industries or market cycles to better understand patterns of returns influenced by sentiment in emerging markets. مالی ‌رفتاری با به چالش‌کشیدن فرضیۀ بازار کارا معتقد است که تصمیم‌گیری سرمایه‌گذاران تنها براساس عقلانیت و حداکثرسازی منافع نیست، بلکه سویه‌های رفتاری، مانند احساسات سرمایه‌گذاران، بر تصمیم‌گیری‌های سرمایه‌گذاری و به ‎‌دنبال آن بر قیمت‌گذاری و بازدهی سهام تأثیرگذار است؛ بنابراین، هدف اصلی این پژوهش، بررسی تأثیر احساسات سرمایه‌گذاران بر روند حرکت بازدۀ مازاد سهام در بازۀ زمانی کوتاه‌مدت و بلند‌مدت در بورس اوراق بهادار تهران است. با به‌کارگیری روش غربال‌گری، نمونه‌‌ای متشکل از 169 شرکت پذیرفته‌‌شده در بورس اوراق بهادار تهران به ‌دست آمد. این نمونه با استفاده از تحلیل رگرسیون چندمتغیره و داده‌های ترکیبی، در بازۀ زمانی 1390 تا 1401 برای فرضیۀ اول و 1390 تا 1399 برای فرضیۀ دوم و سوم بررسی، آزمون و تأثیرات سال و صنعت نیز کنترل شد. نتایج پژوهش نشان داد که احساسات سرمایه‌گذاران در کوتاه‌مدت تأثیر مثبت و در بلندمدت تأثیر منفی بر روند حرکت بازدۀ مازاد سهام دارد. به‌علاوه، احساسات سرمایه‌گذاران تأثیر بیشتری بر روند حرکت بازدۀ مازاد شرکت‌های کوچک‌تر در مقایسه با شرکت‌های بزرگ‌تر در بلندمدت دارد.

https://amf.ui.ac.ir/article_30112_c79a7f38022b9da65f30e946555ce879.pdf

دانشگاه اصفهان مدیریت دارایی و تامین مالی 2383-1189 14 4 2026 12 22 Impact of Capital Structure Speed of Adjustment on the Sticky Expectations تأثیر سرعت تعدیل ساختار سرمایه بر چسبندگی انتظارات اطلاعاتی 91 108 30339 10.22108/amf.2026.146791.2016 FA طیبه واشقانی دانشجوی دکتری، گروه حسابداری، دانشکدۀ اقتصاد، دانشگاه آزاد اسلامی، خمین، ایران محسن رشیدی باغی دانشیار، گروه حسابداری، دانشکده مدیریت و اقتصاد، دانشگاه لرستان، خرم آباد، ایران آذر مسلمی استادیار، گروه حسابداری، دانشکدۀ اقتصاد، دانشگاه آزاد اسلامی، خمین، ایران Journal Article 2025 09 24 Sticky expectations refer to the tendency of expectations to remain unchanged despite the receipt of new information regarding an organization’s status. This effect appears to manifest only in situations that benefit the manager, implying that managers are slow to adjust their decisions in response to new information. This study aims to investigate the stickiness of informational expectations in relation to the capital structure speed of adjustment. To examine this issue, a mixed-data regression model was employed over the period from 2016 to 2023, using data collected from 120 companies listed on the Tehran Stock Exchange to test the research hypotheses. The results indicate the presence of sticky expectations among managers in the sample. Furthermore, the findings reveal that the capital structure speed of adjustment significantly influences managers’ sticky expectations. Finally, the results demonstrate a significant difference between high and low levels of capital structure speed of adjustment with respect to sticky expectations, suggesting that changes in disclosure quality lead to changes in sticky expectations. Managers’ sticky expectations reduce their propensity to adjust forecasts and to respond appropriately to new information. Keywords: Information Expectations, Capital Structure Speed of Adjustment, Disclosure Quality Introduction It is widely argued that individual forecasts are inherently persistent, a phenomenon referred to as expectation stickiness. Stickiness in individual expectations implies that such expectations are influenced by the most recent forecasts made for the same period. This stickiness reflects a form of behavioral bias, wherein individuals may respond disproportionately to surprises or news concerning the current state of affairs, an explanation that aligns closely with the representativeness heuristic. Managers, drawing on expectations formed in response to current information, may revise their earnings forecasts accordingly. Thus, if managers in the current period are influenced by their updated perception of a variable relative to prior expectations, they are likely to extrapolate this effect into the future. As a result, managers adjust their expectations for future performance upward, even when such revisions lack a rational basis. Sticky expectations are characterized by their resistance to change despite the receipt of new information regarding the organization’s status. Notably, this effect appears to arise only in situations that benefit the manager. In other words, managers are slow to adjust their decisions when confronted with new information. Against this backdrop, the purpose of the present study is to investigate the stickiness of informational expectations in relation to the capital structure speed of adjustment. Materials & Methods Given that the findings of this study can be utilized in decision-making processes, the research is classified as applied in terms of its objective, as applied research aims to develop practical knowledge within a specific domain. In terms of data collection, this study is descriptive. Descriptive research may be conducted either to gain a deeper understanding of existing conditions or to support decision-making processes. Within the various classifications of descriptive research, the present study is correlational in nature. A mixed-data regression model was employed over the period from 2016 to 2023, using data collected from 120 companies listed on the Tehran Stock Exchange to test the research hypotheses. Data were gathered from the financial statements and reports of the listed companies using an archival method, and estimations were performed using a pooled data approach. Findings The results indicate the presence of stickiness in managers’ expectations among the companies under study. Furthermore, the findings pertaining to the second hypothesis reveal that the speed of capital structure adjustment exerts a significant effect on managers’ sticky expectations. Finally, the results related to the third hypothesis demonstrate a significant difference between high and low classes of capital structure adjustment speed with respect to sticky expectations, suggesting that changes in disclosure quality are associated with changes in the stickiness of expectations. Discussion & Conclusion This study examined informational expectation stickiness in relation to the speed of capital structure adjustment. According to general equilibrium theory, information is assumed to be timeless and instantaneous, implying that it is available without delay. In the real economy, however, the dissemination and acquisition of information involve time lags. In other words, when a manager seeks to gather relevant information, the process incurs not only costs but also time. Due to these delays in information acquisition, expectations cannot be revised immediately or within a short period. As a result of the costs and timing constraints associated with information processing, managers devote more time to collecting new data, making it difficult to respond promptly to changes in economic performance. Consequently, managerial expectations exhibit stickiness. Such sticky expectations reduce managers’ propensity to adjust forecasts and to respond appropriately to new information. More broadly, the quality of information disclosure and the capital structure speed of adjustment are important considerations for financial policymaking and the development of reporting standards. Emphasizing improvements in these areas can enhance companies’ financial responsiveness, promote transparency, and reduce suboptimal behaviors driven by outdated expectations. Given the demonstrated stickiness in the expectations of managers within the firms under study, it is recommended that managers, rather than attempting to construct a purely rational forecast independently, incorporate information regarding the expectations of other managers when forming their own projections. هدف: انتظارات چسبنده سبب می‎‌شود برخلاف دریافت اطلاعات جدید مرتبط با وضعیت سازمان، تصمیم‎‌گیری‎‌ها ثابت بماند. این اثر فقط در موقعیت‌هایی وجود دارد که در راستای منافع مدیر باشد. به عبارتی، مدیر نسبت‌به تعدیل تصمیمات خود هم‌زمان با دریافت اطلاعات جدید، به‌کندی عمل می‎‌کند. هدف از این پژوهش بررسی چسبندگی انتظارات اطلاعاتی بر مبنای سرعت تعدیل ساختار سرمایه است. به‌منظور بررسی موضوع موردمطالعه، در دورۀ زمانی 1395 تا 1402 داده‎‌های 120 شرکت پذیرفته‌شده در بورس اوراق بهادار تهران جمع‌آوری و برای آزمون فرضیه‌ها از رویکرد داده‎‌های تلفیقی استفاده شد. نتایج پژوهش نشان‎‌دهندۀ وجود چسبندگی انتظارات در تصمیمات مدیران است. نتایج حاکی‌ازآن است که سرعت تعدیل ساختار سرمایه اثر معناداری بر چسبندگی انتظارات اطلاعاتی مدیران شرکت‎‌های بورسی دارد؛ درنهایت، می‎‌توان ادعا کرد که بین طبقه‌های بالا و پایین سرعت تعدیل ساختار سرمایه از بُعد چسبندگی انتظارات، تفاوت معناداری وجود دارد و می‎‌توان ابراز داشت که تغییرات در کیفیت افشا به تغییر در چسبندگی انتظارات منجر می‎‌شود. چسبندگی انتظارات مدیران نیز به کاهش تمایل به تعدیل پیش‎‌بینی‎‌ها و واکنش مناسب به اخبار جدید منجر می‎‌شود.

https://amf.ui.ac.ir/article_30339_a89f95977cc756369e183feb66dd17bb.pdf

دانشگاه اصفهان مدیریت دارایی و تامین مالی 2383-1189 14 4 2026 12 22 Comparison of Two Machine Learning–Based Algorithms for the Two Stages of a Pairs Trading Strategy مقایسه دو الگوریتم مبتنی بر یادگیری ماشینی برای دو بخش راهبرد معاملات زوجی 109 132 30255 10.22108/amf.2026.146240.2006 FA سمیرا اسدیان دانشجوی دکتری، گروه حسابداری، دانشکده اقتصاد مدیریت و حسابداری، دانشگاه یزد، یزد، ایران حجت الله صادقی دانشیار، گروه مدیریت صنعتی، دانشکده اقتصاد مدیریت و حسابداری، دانشگاه یزد، یزد، ایران داریوش دموری دانشیار، گروه حسابداری و مالی، دانشکده اقتصاد مدیریت و حسابداری، دانشگاه یزد، یزد، ایران Journal Article 2025 08 06 Market participants have shown increasing interest in quantitative trading models and the intelligent application of data science. These approaches can enhance the effectiveness of trading strategies such as pairs trading—a valuable investment method even during bear markets. This strategy comprises two key steps: selecting two securities (pair formation) and detecting anomalies in the price spread between them (trading execution). We evaluate two machine learning approaches to identify the most effective algorithm for each stage. To efficiently group related securities and uncover high-potential pairs—a task that even skilled investors may find challenging—we employ two density-based clustering methods: DBSCAN (Density-Based Spatial Clustering of Applications with Noise) and OPTICS (Ordering Points to Identify the Clustering Structure). These algorithms define the search space by identifying meaningful clusters of securities. To reduce portfolio drawdowns while maximizing returns after detecting price divergences, we implement two time series forecasting models: Long Short-Term Memory (LSTM) and LSTM encoder-decoder. OPTICS outperforms DBSCAN, demonstrating greater efficiency with fewer variables, a higher Sharpe ratio, and a larger proportion of profitable pairs. The LSTM encoder-decoder outperforms the standard LSTM model, delivering higher returns, an improved Sharpe ratio, and fewer days of portfolio decline. This study introduces a novel approach by leveraging machine learning models for both phases of the pairs trading strategy while optimizing model selection. Other distinctive features include the use of high-frequency intraday data (5‑minute intervals) across all market stocks (rather than a specific stock or industry), and a focus on net returns after accounting for transaction costs. Keywords Pairs Trading Strategy, Machine Learning, Density-Based Clustering, Forecasting-Based Model Introduction Pairs trading was first introduced to the financial literature by Gatev et al. (2006) and involves two steps: identifying two securities (a pair) and detecting an irregularity in the price gap between them (taking a trade). Given its proven robustness during market downturns and broad adoption (Do & Faff, 2010; Jacobs & Weber, 2015; Clegg & Krauss, 2018), the application of intelligent data science methods offers a promising path to enhance pairs trading performance. In the pair formation phase, we use two density-based clustering algorithms—DBSCAN and OPTICS—to determine the search space and identify clusters among a large number of securities, a task that is otherwise difficult to perform (Ester et al., 1996; Ankerst et al., 1999). In the trading phase, we employ two time-series prediction models—Long Short-Term Memory (LSTM) and an LSTM encoder-decoder network—to shorten portfolio drawdown periods and boost returns. The key contribution of this research lies in its systematic application of multiple machine learning algorithms across every phase of the strategy, aiming to identify the optimal models and enhance overall performance through predictive analytics. Accounting for transaction costs enables the reporting of realistic net profitability. Furthermore, the use of 5-minute intraday data significantly improves the accuracy of our findings. Materials & Methods The data consist of 111 stocks traded on the Tehran Stock Exchange and the IranFaraBourse over the period 2014 to 2019. To ensure liquidity conditions consistent with the criteria adopted by Gatev et al. (2006) and Do & Faff (2012), data imputation was performed using the tsrobprep open-source package in R software. To create meaningful clusters, we first performed dimensionality reduction using principal component analysis (PCA), followed by the application of DBSCAN and OPTICS clustering algorithms. Subsequently, four conditions were applied: (1) the components of each pair are co-integrated; (2) the Hurst component of the pair's price gap exhibits mean-reverting properties; (3) the price gap of each pair shows convergence and divergence over appropriate periods; and (4) the mean reversion of the pair's price gap occurs with sufficient frequency. The data were divided into a formation period and a trading period. The work includes three different test portfolios of securities: Portfolio 1 includes all pairs identified during the formation period; Portfolio 2 includes pairs with positive results; and Portfolio 3 is limited to investing in the 10 pairs with the highest returns in the validation set. To compare the robustness of the standard threshold-based model with the proposed prediction-based model, simulations were carried out using the LSTM and LSTM encoder-decoder models. All pairs in the portfolio were equally weighted. The code developed for this work was implemented in Python. Findings The first step in applying the proposed approach to stock clustering involves defining an appropriate number of principal components to reduce the dimensionality of the original data, which was set to five. OPTICS offers two distinct advantages over DBSCAN: (1) it effectively handles data clusters of varying densities, and (2) it eliminates the challenge of determining the optimal ε parameter. Analysis of the selected pairs shows that this method yields a promising portfolio with a satisfactory profit margin and a high average Sharpe ratio of 10.57. The results of the prediction-based trading models (LSTM and LSTM encoder-decoder) using the OPTICS algorithm for the period from April 2017 to March 2019 are presented in the table 1, alongside the results for the standard threshold-based model. In the standard trading model, the portfolio drawdown is significantly shorter; however, the drawdown in the LSTM encoder-decoder model is adequate and substantially shorter than that of the other model. The longer drawdown period for the standard LSTM is 190 days. The portfolio performs considerably better in terms of total return on investment (21,993.8%) and Sharpe ratio (35.50). The superior results from the LSTM encoder-decoder suggest that multi-stage prediction is effective in these settings. Table 1. Comparing trading results using a 3-year formation period LSTM encoder-decoder-based model LSTM-based model standard Trading model parameter validation 12 12 2 Drawdown numbers -0.51 2.18 6.7 SR 616.28 29817.4 7911.1 ROI(%) 170.24 33.97 8.43 MDD(%) 9829(9749-80) 9044(8983-62) 46(12-34) Trading numbers(+, -) 9.1 22.7 100 Profitable pairs (%) test 29 190 10 Drawdown numbers 50.35 2.18 0.53 SR 21993.8 -90.12 1918.9 ROI(%) 79.17 99.80 23.13 MDD(%) 150(143-7) 1196(1162-34) 25(12-13) Trading numbers(+, -) 100.0 0 86.4 Profitable pairs (%) Discussion & conclusion In comparing the results of this study with those of others, the work of Sarmento and Horta (2020) introduced advanced predictive modeling techniques—namely LSTM and its encoder-decoder variant—to the field of US ETF trading analysis. While these models successfully shortened portfolio drawdown periods, they also reduced overall returns. In their study, the traditional securities portfolio significantly outperformed the models in both total return and Sharpe ratio. Therefore, key features of the Iranian capital market's structure—such as its price fluctuation limits, base volume trading rules, and the surge in retail investor participation during 2019–2020—may be the primary reasons for the differing outcomes observed in the present study. Scientifically, however, this outcome is better explained by the limited adoption of machine learning models in the Iranian capital market. Even the use of classical algorithmic trading remains minimal, making the application of advanced models exceedingly rare. Flori and Regoli (2021) employed LSTM to analyze nonlinear interdependencies within and between financial time series for forecasting S&P 500 stock market performance. Their LSTM framework's predictive accuracy was benchmarked against several common machine learning models, including logistic regression, gradient boosted trees, and feedforward neural networks. The purpose of the LSTM application was to forecast the probability of a stock generating excess returns compared to similar stocks in the short term. Their analysis indicates that investment strategies incorporating such forecasts are effective for improving portfolio performance, as they generate predictive signals with exploitable information beyond basic price-yield gaps. باتوجه‌به علاقۀ مشارکت‌کنندگان بازار به مدل‌های معاملاتی کمّی و استفاده از کاربردهای هوشمندانۀ علم داده می‌توان عملکرد راهبرد‌های معاملاتی ازجمله معاملات زوجی را بهبود بخشید که ابزار سرمایه‌گذاری خوبی حتی در بازارهای نزولی است. با در نظر گرفتن دو مرحلۀ این راهبرد شامل شناسایی دو ورقۀ بهادار (یک زوج) و کشف بی‎‌نظمی در شکاف قیمتی بین آنها (انجام معامله)،‎‌ دو روش یادگیری ماشینی برای انتخاب الگوریتم بهتر در هر مرحله مقایسه شد. برای تعیین فضای جست‎‌وجو که سعی بر گروه‎‌بندی اوراق‌بهادار مرتبط در خوشه‎‌ها و شناسایی زوج‎‌های برتر دارد، از دو الگوریتم خوشه‌بندی مبتنی بر چگالی شامل خوشه‎‌بندی فاصله‎‌ای مبتنی بر چگالیِ کاربردها با نوفه (دی‌بی‌اسکن) و مرتب‌سازی نقاط برای شناسایی ساختار خوشه‌بندی (آپتیکز) استفاده شد که در غیر این‎‌صورت شناسایی آن حتی برای سرمایه‎‌گذار باتجربه هم دشوار است. از طرفی برای به‌ حداقل رساندن تعداد روزهای کاهش ارزش سبد به‌همراه افزایش بازده پس از یافتن شکاف قیمتی، از دو مدل معاملاتی مبتنی بر پیش‎‌بینی سری‎‌زمانی، حافظۀ کوتاه‎‌مدت طولانی (ال‌اس‌تی‌ام) و حافظۀ کوتاه‎‌مدت طولانی رمزگذار _ رمزگشا استفاده شد. برتری آپتیکز به دی‌بی‌اسکن در تعداد متغیرهای کمتر و نسبت شارپ بالا و درصد زوج‌های سودآور بالاتر مشهود است. مدل ال‌اس‌تی‌ام رمزگذار _ رمزگشا در کل در کسب بازدهی و نسبت شارپ، عملکرد بهتر و دربارۀ کاهش تعداد روزهای رکودی سبد بالاتر از مدل ال‌اس‌تی‌ام بود. استفاده از داده‌های با تکرار زیاد (5دقیقه‌ای) (تمامی سهام ‌بازار و نه سهم یا صنعت خاصی) به همراه استفاده از مدل‌های یادگیری ماشینی برای افزایش سرعت در تصمیم‌گیری و ارائۀ بازده‌های خالص به‌منظور بررسی مدل‌ها از موارد مهم این کار است.

https://amf.ui.ac.ir/article_30255_06b8e3fcd2384a38e218c31548bce28e.pdf