ABSTRACT This study examines behavioural differences in risk aversion (variance risk), prudence (downside risk), and temperance (tail risk) between public and private sector employees, employing higher-order risk preference theory. Using two monetary-incentivized behavioural tasks (Multiple Price List and Deck-Schlesinger Lottery) with 1000 participants in Japan, we compare risk behaviours across sectors. Results demonstrate that public employees exhibit significantly higher temperance after accounting for individual-level covariates, indicating stronger aversion to extreme outcomes. Sectoral differences in risk aversion and prudence become insignificant once public service motivation is controlled. These findings highlight the importance of distinguishing multiple risk dimensions in sectoral comparisons.

This paper offers a hybrid forecasting approach that merges a local-level state space Kalman filter with a Long-Short-Term Memory (LSTM) neural network to assess the downside risk of the Botswana Pula versus the US Dollar (BWP/USD). Inspired by the inability of conventional econometric models to capture complex latent structural shifts and nonlinear patterns, our architecure uses a bottom-up hierarchical methodology in which the smoothed level component of the exchange rate is isolated by the Kalman filter and subsequently fed into the LSTM architecture. Three key indicators for assessing downside risk—Maximum Drawdown (MDD), Conditional Drawdown-at-Risk (CDaR), and Downside Deviation—are used to assess model performance across various time-frames (7, 30, 90, 180, and 240 days). As confirmed by Kupiec and Christoffersen’s backtesting processes, the findings show a high degree of alignment between projected and actual values, with negligible downside deviation bias and robust calibration. Moreover, global economic and geopolitical shocks, such as the COVID-19 pandemic, the Russia–Ukraine conflict, and the 2015–2016 Shanghai Stock Exchange crash, are important factors that influence exchange rate volatility, according to explainable artificial intelligence techniques, particularly SHAP (SHapley Additive exPlanations) analysis. Downside risk is also greatly increased by regional currency links, especially the impact of the ZAR/BWP exchange rate. On the other hand, domestic temporal variables, such as week, quarter, and month, have very little impact. These results emphasise how Botswana’s currency rate is structurally vulnerable to external shocks and how crucial it is to include both global and regional considerations in risk analysis. The research concludes that the accuracy and transparency of projections for exchange rate risk significantly improve when practical filtering is combined with deep learning and explainable AI. To improve macroeconomic resilience and guide successful financial risk management plans in emerging market environments, policymakers are advised to employ AI-driven forecasting techniques, enhance regional monetary coordination, and set up real-set learning systems.

Cryptocurrency markets are characterized by extreme volatility, fat-tailed return distributions, and frequent regime shifts, challenging traditional mean–variance portfolio optimization. In such environments, downside risk management becomes central, and tail-sensitive measures such as Conditional Value-at-Risk (CVaR) are increasingly adopted. However, empirical evidence remains mixed regarding whether CVaR-based strategies provide consistent protection across market regimes and tail depths. This study conducts a comprehensive empirical evaluation of tail-risk-based portfolio strategies using cryptocurrency data from 2018 to 2025. A rolling-window back-testing framework with weekly rebalancing is employed. We compare traditional benchmarks, moment-based and robust CVaR strategies, regime-dependent CVaR optimization, regression-enhanced ES–CVaR hybrids, and reinforcement learning-based CVaR policies. Performance is evaluated using mean return, volatility, CVaR at multiple confidence levels (90%, 95%, and 99%), and maximum drawdown. Market regimes are identified through volatility-based rules, and robustness is assessed via sensitivity analysis and block-bootstrap confidence intervals. The results show that no single strategy dominates across all conditions. Hybrid ES–Reg–CVaR strategies provide stable protection under moderate tail risk, reinforcement learning-based CVaR strategies adapt better to extreme tails, and regime-based CVaR optimization consistently limits drawdowns during stress periods. These findings demonstrate that effective CVaR-based portfolio management in cryptocurrency markets requires a regime- and tail-depth-dependent approach rather than a universal optimization rule.

ABSTRACT This study constructs a gambling preference index. Our primary objective involves examining the relationship between gambling preference and tail risk in crude oil futures. We further evaluate the profitability of portfolios built upon this preference. Data for WTI and Brent crude oil futures were collected from Investing.com and the FRED database to underpin these analyses. First, SCAD, MCP, and ReLASSO penalized regressions demonstrate that gambling preference captures tail risk more effectively than various macroeconomic and financial factors. Subsequently, Diks-Panchenko causal analysis confirms that gambling preference significantly predicts tail risk. We assess the practical role of gambling preference by embedding it into a mean-risk asset allocation framework. Adjusting the weights of crude oil futures against U.S. Treasury bonds based on gambling preference yields returns well above the market benchmark. Such an advantage strengthens with lower risk aversion. Overall, our gambling preference index characterizes the phenomenon where investors incur extreme left-tail risk to achieve superior market returns. In practice, this metric serves as a proxy for market sentiment and an early warning indicator for price downside risk.

ABSTRACT This study aimed to explore the interactions between corporate quality and downside risk. We identified the bidirectional causality through Granger causality test, then employed lagged one period panel data regressions. The empirical results revealed that all downside risk measures exhibited consistent explanatory power in corporate quality and remained robust under different parameters settings and GMM tests. This study contributes to the literature by offering empirical evidence linking downside risk to multidimensional corporate quality in an emerging market context. Practical implications are drawn for investors, corporate managers, and policymakers aiming to enhance financial resilience, strengthen risk management, and improve market-based screening mechanisms.

ABSTRACT This study examines extreme downside risk spillovers between the global carbon market and major energy markets and evaluates their predictive value. Using daily data from 2013 to 2024, we estimate tail‐risk dependence with the MVMQ‐CAViaR model and quantify the dynamic transmission of extreme shocks via pseudo‐quantile impulse responses. Our results document strong and asymmetric spillovers between carbon and major energy markets. A bidirectional forecasting framework using Quantile Regression Forests, Quantile Gradient Boosting, and Quantile Regression Neural Networks results in substantial out‐of‐sample gains, confirmed by Diebold–Mariano tests. These findings suggest that regulators and market operators should integrate carbon–energy tail‐risk linkages into early‐warning systems and cross‐market surveillance frameworks, so materially enhance the detection of extreme risk events. The results also highlight the value of adopting machine learning‐based quantile models in policy settings where timely assessment of systemic risk is essential.

The integration of sustainability factors into investment decisions has transformed modern finance, with investors increasingly seeking to align their portfolios with environmental and societal values. The critical question remains as to whether the sustainability factor is priced in emerging markets. This study aims to provide a comprehensive analysis of the risk-adjusted return performance of three sustainability indexes of the emerging Indian market: NIFTY environmental, social and governance index (N100ESG), S&P BSE carbon-based thematic index (CARBONEX) and S&P BSE GREENEX (GREENEX) in comparison to the broad-based NSE 100 index (NIFTY100). The sample period for the analysis spans from January 2015 to August 2024. We have used risk-adjusted measures to evaluate the performance of sustainability indices. Additionally, we have analyzed downside risk, market-timing ability and volatility persistence using various generalized autoregressive conditional heteroskedasticity (GARCH)-type models. The findings indicate that sustainable investments offer competitive returns with better downside protection, especially for long-term investors. Among the indices, N100ESG demonstrated superior overall performance, while GREENEX stood out for risk–return resilience. However, reliance on market-cap criteria may dilute ESG purity. A more nuanced regulatory framework is essential to enhance the effectiveness of sustainable investing in India.

This study examines how aggregate financial risk tolerance (FRT), measured from repeated survey responses, co-evolves with stock-market dynamics over time. The observed FRT index is treated as a noisy preference signal containing both gradual drift and episodic deviations, and its market relevance is evaluated under time variation, frequency components, and stress regimes. Using monthly data that align the survey-based FRT index with market returns and risk measures, a three-part econometric design is implemented. First, a time-varying parameter VAR (TVP-VAR) characterizes bidirectional, non-constant linkages between FRT and market outcomes. Second, signal-extraction methods decompose FRT into a smooth “normal” component and a high-frequency “abnormal” component (with robustness to alternative filters) to test whether short-run deviations contain distinct information for volatility and downside risk. Third, a Markov-switching specification assesses state dependence by testing whether the FRT–market relationship differs between low-stress and high-stress regimes. Across specifications, the FRT–market linkage is strongly state dependent: the sign and magnitude of FRT effects drift over time and differ across regimes, with high-frequency FRT deviations aligning more closely with risk dynamics than the smooth component. Predictive validation is provided via out-of-sample forecasting of next-month market risk using elastic net and gradient boosting relative to an AR(1) benchmark; explainability analysis (SHAP) indicates that abnormal FRT contributes incremental predictive content beyond standard market-state variables. Overall, the framework offers a mathematically transparent approach to modeling survey-based preference signals in markets and supports regime-aware forecasting and risk-management applications.

ABSTRACT This study analyzes downside risk and nonlinear dependence in agricultural commodity futures using a hybrid framework that integrates Self‐Organizing Maps (SOMs) with Copula‐based dependence modeling. Agricultural returns exhibit asymmetric behavior, making linear correlation inadequate for risk assessment. The SOM identifies distinct market regimes based on return dynamics and volatility structure, while Student‐ and Clayton copulas quantify symmetric and lower‐tail dependence within each regime. Results show a clear escalation of dependence from tranquil to crisis states, with tail‐dependence coefficients rising monotonically across SOM clusters. The Student‐ copula captures symmetric co‐movements in extreme returns, whereas the Clayton copula highlights strong joint downside risk during high‐volatility phases. These patterns confirm that diversification benefits across agricultural commodities weaken substantially under stress. The proposed SOM–Copula hybrid framework provides a regime‐sensitive approach to modeling tail interdependence in commodity markets.

ABSTRACT We introduce a state‐dependent hedging framework for pairs trading that captures the nonlinear return dependence between stocks and their benchmarks. We reinterpret static pairs trading as a strategy with a state‐dependent hedge ratio that varies with return volatility. This design enables investors to over‐hedge against large return shocks. The augmented strategy shows comparable investment performance but lower downside risk, with pronounced outperformance in recent and highly volatile periods. The strategy's effectiveness appears to stem from managing cash‐flow risks tied to turbulent relative price spreads and maintaining exposure to industry momentum.

In deregulated electricity markets, Generation Companies (GENCOs) are exposed to substantial financial risk due to volatile and uncertain electricity prices. Traditional generation asset valuation approaches, which rely primarily on expected profit, fail to adequately capture downside risk under market uncertainty. This study proposes an integrated risk-aware framework for generation asset valuation by embedding Value-at-Risk (VaR) into a Price-Based Unit Commitment (PBUC) model. VaR is employed to quantify potential profit losses at different confidence levels, enabling GENCOs to explicitly assess downside exposure associated with electricity price fluctuations. Spot price uncertainty is modeled using the Delta-Normal approach based on historical PJM market data. The resulting nonlinear mixed-integer optimization problem is solved using an Improved Immune Algorithm (IIA) enhanced with the Taguchi Method to improve convergence stability and solution diversity. Case studies on the IEEE 15-unit system demonstrate that the proposed IIA consistently outperforms conventional evolutionary algorithms in terms of profitability, robustness, and convergence reliability. The VaR analysis further reveals pronounced left-tail risk in profit distributions, particularly during peak-load periods, highlighting the importance of risk-adjusted commitment strategies. The proposed framework provides a practical decision-support tool for GENCOs to balance profitability and downside risk in competitive electricity markets.

Quantitative asset allocation remains a critical challenge in modern finance, particularly due to the inherent uncertainty of expected returns (μ) and the sensitivity of portfolio outcomes to the stability of portfolio weights. This study conducts a comparative empirical analysis of three portfolio strategies—MVO, Static RP, and Dynamic RP—using a long-only portfolio of eleven highly liquid assets, consisting of U.S. large-cap equities and gold, over the period 2015–2025. Results from historical backtesting indicate maintaining a competitive Sharpe ratio (1.418) and the lowest Maximum Drawdown (−0.2770) relative to Markowitz MVO (−0.3120) and Static RP (−0.2788). Although Markowitz delivers the numerically highest Sharpe ratio (1.655), this advantage is largely driven by in-sample optimization, with limited robustness under realistic implementation settings. In contrast, Dynamic RP demonstrates superior downside risk management, weight stability, and adaptability to changing market conditions, suggesting a more practical and resilient framework for real-world investment applications. Overall, the findings indicate that Dynamic Risk Parity provides an effective and robust alternative to traditional mean-variance optimization, offering investors a strategy that balances return potential, risk mitigation, and portfolio stability, while addressing key limitations of classical MVO approaches.

Type of the article: Research ArticleAbstractThe increasing behavioral volatility and informational complexity of emerging stock markets such as Vietnam create a critical need for more advanced analytical approaches to identify reliable momentum signals. This study aims to develop and validate an integrated momentum-based trading strategy specifically designed for the Vietnamese stock market. Using price and trading volume data for all stocks listed on the VNINDEX from January 2015 to February 2025, the methodology combines permutation-based entropy measures to capture short-term structural patterns with a formation–holding period framework to analyze medium- and long-term dynamics through Continuing Overreaction. The empirical results reveal a pronounced structural divergence in momentum behavior across investment horizons. Short-term momentum is persistent and strongly associated with low-complexity price and volume patterns, indicating coordinated behavioral trading and temporary predictability. In contrast, medium- and long-term Continuing Overreaction effects exhibit consistently negative values across various formation and holding horizons, suggesting that excess trading intensity leads to systematic mean reversion rather than sustained momentum. Backtesting over the period from January 2023 to February 2025 demonstrates that the proposed integrated strategy substantially outperforms a passive VNINDEX buy-and-hold benchmark, achieving a Sharpe ratio of 3.96 compared to 0.64 for the market. The superior performance remains robust across alternative portfolio construction settings and reflects improved downside risk control rather than increased return volatility. These findings indicate that integrating entropy-based complexity measures with volume-driven behavioral indicators provides a more effective framework for enhancing risk-adjusted returns in emerging stock markets.

Cryptocurrency financial markets are characterized by high volatility and non-stationary price dynamics, posing significant challenges to traditional portfolio optimization techniques that rely on static risk–return assumptions. In such environments, existing methods often struggle to generalize and adapt effectively, leading to suboptimal performance and increased downside risk. To address these limitations, this paper proposes a novel adaptive portfolio optimization framework that integrates Generative Adversarial Networks (GANs) for synthetic data augmentation with a state-of-the-art Soft Actor-Critic (SAC) deep reinforcement learning (DRL) agent. By augmenting real historical OHLC data with realistic TimeGAN-generated price sequences, the proposed approach exposes the DRL agent to a broader range of market scenarios, thereby improving generalization and mitigating overfitting. A convolutional neural network (CNN) feature extractor captures deep temporal dependencies, while causal and dilated convolutions model complex inter-asset correlations. Empirical results demonstrate that the proposed GAN–SAC hybrid consistently outperforms conventional strategies and the baseline Deep Portfolio Optimization (DPO) model, achieving a higher Accumulative Portfolio Value (APV) of 53.72, an improved Sharpe Ratio of 0.0980, and a reduced Maximum Drawdown (MDD) of 28.5%. These findings confirm the effectiveness of combining generative models and DRL to develop robust, adaptive portfolio strategies capable of navigating highly volatile cryptocurrency markets, with practical implications for next-generation algorithmic trading systems requiring enhanced resilience and dynamic risk control.

ABSTRACT This study develops and validates an integrated soil–land–climate (SLC) framework to predict farm household income in South Sindh and South Punjab, Pakistan. Using a Multinomial Endogenous Switching Regression (MESR) model, we assess how soil fertility, water scarcity, and climate stress impact agricultural productivity and income. Results show that a one‐unit increase in soil fertility index raises farm income by 1.39 units ( p < 0.01), while water availability increases income by 2.43 units ( p < 0.05). Climate change perception demonstrates the strongest effect, boosting income by 7.39 units ( p < 0.01). CSA adoption reduces income risk by 49% ( p < 0.01) and revenue skewness by 38% ( p < 0.05). The SLC framework revealed feedback loops in which water scarcity accelerated soil salinization ( r = 0.62, p < 0.01). The joint adoption of CSA practices results in a 45.9% increase in income and a 49.0% reduction in downside risk. The validity of the MESR model was confirmed with robust statistical results. Soil fertility (coefficient = 0.23) and farm size (coefficient = 0.18) are key factors influencing farm income, while rainfall variability (coefficient = −0.21) shows a climate variability impact. Policy simulations indicate that improving soil health raises annual income, while drip irrigation subsidies targeting farms > 8 km from markets yield 3:1 benefit–cost ratios. This study provides evidence for climate adaptation policies in Pakistan by recommending targeted subsidies for drip irrigation, soil amendments, and strengthening of FBOs.

Introduction Rice is a major staple and commercial crop in Tanzania, playing a vital role in ensuring food security, supporting rural livelihoods, and contributing to national economic growth. However, smallholder productivity remains constrained by suboptimal input use and agroecological variability. Among the strategies debated to improve yields is the use of fertilizers, both organic and inorganic, whose effectiveness varies with climate, soil type, and farming system. Methodology This study employed a non-parametric stochastic simulation approach to model the impact of fertilizer use on rice productivity using nationally representative data from the 2019/20 National Sample Census of Agriculture (NSCA). Farmers were grouped into three categories: non-fertilizer users, organic fertilizer users, and inorganic fertilizer users. Yield performance was simulated and evaluated against two benchmarks: the national threshold of 3.0 t/ha and the global standard of 4.5 t/ha. Simulations were stratified by Agroecological Zone (AEZ) and administrative region, including Mainland Tanzania and Zanzibar. Results Simulation results indicate that inorganic fertilizer users achieved the highest probabilities of exceeding both productivity thresholds: 28% for yields >3.0 t/ha and 11% for yields >4.5 t/ha. Organic fertilizer users followed closely with 26 and 10% probabilities, respectively. In contrast, non-fertilizer users showed significantly lower probabilities: 19 and 5%. Downside risk (the likelihood of yield falling below the threshold) was also lowest among inorganic users. Spatial differences were observed, with farms in Mainland Tanzania generally performing better than those in Zanzibar. Variability across AEZs further emphasized the influence of site-specific factors. Discussion The findings underscore that both inorganic and organic fertilizers significantly enhance rice productivity, although their impacts vary by region. Inorganic fertilizers have a more pronounced effect, particularly in minimizing downside yield risks. However, a one-size-fits-all strategy may be ineffective due to regional heterogeneity. Therefore, policies should prioritize region-specific fertilizer strategies, integrated soil fertility management (ISFM), input subsidy reforms, and strengthened agricultural extension services. These interventions can help advance climate-resilient rice production and contribute meaningfully to Sustainable Development Goals (SDGs) 2 (Zero Hunger) and 13 (Climate Action).

We investigate investor overconfidence in the age of artificially intelligent coincident with human–algorithmic and hybrid decision‐making models on the Pakistan Stock Exchange (PSX). Leveraging behavioral finance literature and advances in AI-based investment tools, the paper explores whether algorithmic behaviors alleviate or change overconfidence when human judgments persist. Based on panel data for PSX investors, 2020:2025, overconfidence is proxied by turnover, holding bias and relative deviation from trading algorithms. The empirical evidence shows that human-only investors have a higher turnover, more portfolio concentration and earn less risk-adjusted returns than algorithm-based portfolios. AI-driven portfolios exhibit better diversification and lower downside risk compared to traditional portfolios, but hybrid investors tend to ignore machine suggestions after an initial period of profit, which is consistent with learning-based overconfidence and illusion of control. Regressions suggest that overconfidence undermines the efficiency gains of AI via discretionary intervention, resulting in higher volatilities and more pronounced draw-downs when under financial stress. In general, the results imply that AI doesn’t remove behavioral biases but rather re-sculpts their manifestation in hybrid decision worlds. Our paper extends overconfidence theory into AI-mediated markets and has significant implications for investors, financial institutions and regulators in emerging markets.

Exchange-traded funds (ETFs) provide low-cost, liquid access to broad equity and fixed-income exposures, including rapidly growing Asian and Asia-focused markets. Yet the academic evidence on Asian ETF portfolio construction remains fragmented, often limited to narrow country samples and centered on mean–variance trade-offs and standard performance statistics, with comparatively less emphasis on downside tail risk and on implementable long-only versus long–short designs under leverage constraints. This study examines the performance and risk characteristics of 29 Asian and Asia-focused ETFs over 2014–2025 and evaluates whether optimization using variance-based and tail-sensitive risk measures improves portfolio outcomes relative to a simple, implementable benchmark. We construct Markowitz mean–variance and conditional value-at-risk (CVaR) efficient frontiers and implement six optimized portfolios at the 95% and 99% tail levels under long-only and long–short configurations with leverage up to 30%. Performance is evaluated relative to an equally weighted Asian ETF benchmark using the Sharpe ratio and tail-sensitive measures, including the Rachev ratio and the stable tail adjusted return (STARR), complemented by fat-tail diagnostics based on the Hill tail-index estimator. The empirical results show that optimization improves efficiency relative to equal weighting in risk-adjusted terms and that moderate leverage can increase returns but typically amplifies volatility, dispersion, and drawdowns. Taken together, the evidence indicates that risk-measure choice materially affects portfolio composition and realized outcomes, with tail-based optimization generally producing more robust allocations than mean–variance approaches when downside risk is a primary concern.

ESG (Environmental, Social, and Governance) investment has been building up as a values based special purpose strategy to a theoretically sound and empirically valid constituent of the contemporary portfolios. The current research summary provides a conceptual description of the observed empirical steps through which ESG characteristic can influence the prices of assets, the communications of risk and capital decision. In line with nonpecuniary utility, information asymmetry, and stakeholder theory models, we examine empirical evidence concerning the presence or absence of pricing of ESG attributes as risk factors, safeguarding of downside risk, or, merely,, simply industry and firm-specific factors. We research in terms of techniques methodological instruments of econometric identification panel regressions, quasi-natural experiments, and factor-model extensions and novel methods of forecasting ESG-adjusted returns with machine-learning and identifying non-linear relationships. The literature has shown that the ESG integration is always associated with reduced volatility and tail-risk exposure but the return premia is sporadic and is contingent on the design of the measure. The review also displays the increased importance of the ESG factors in the decision in allocating venture capital particularly venture capital in capital-intensive green technology. The typical issues include the data fragmentation, the difference in scores, the absence of inference of causality and the complicatedness of the dynamics modeling of the formation of ESG factors. Our research areas of interest will include standardized ESG data construction, and introduction of ESG into multi-factor models of asset-pricing, and construction of ESG valuation of more diversity of assets other than household and alternative assets.

Overfitting remains a critical challenge in data-driven financial modelling, where machine learning (ML) systems learn spurious patterns in historical prices and fail out of sample and in deployment. This paper introduces the GT-Score, a composite objective function that integrates performance, statistical significance, consistency, and downside risk to guide optimization toward more robust trading strategies. This approach directly addresses critical pitfalls in quantitative strategy development, specifically data snooping during optimization and the unreliability of statistical inference under non-normal return distributions. Using historical stock data for 50 S&P 500 companies spanning 2010–2024, we conduct an empirical evaluation that includes walk-forward validation with nine sequential time splits and a Monte Carlo study with 15 random seeds across three trading strategies. In walk-forward validation, GT-Score improves the generalization ratio (validation return divided by training return) by 98% relative to baseline objective functions. Paired statistical tests on Monte Carlo out-of-sample returns indicate statistically detectable differences between objective functions (p < 0.01 for comparisons with Sortino and Simple), with small effect sizes. These results suggest that embedding an anti-overfitting structure into the objective can improve the reliability of backtests in quantitative research.