Aug 2026· American Journal of Financial Technology and Innovation· 0 citations· 22 references
Abstract
Classical put-overlays have long been treated as a reliable hedge against tail risk but the market conditions of 2025 expose their limits in ways that theory didn’t fully anticipate. This paper examines where these strategies break down: in markets defined by elevated volatility, wide bid-ask spreads, and structural frictions that quietly erode the protection investors thought they’d bought. Traditional hedging methods, which rely on the systematic purchase of out-of-the-money (OTM) options, are increasingly hampered by high premiums and reliance on static volatility assumptions. During the significant geopolitical disruptions of 2025, most notably the “Tariff Shock” of April, these traditional models proved inadequate, suffering from “premium bleed” and an inability to account for discontinuous market gaps. To address these systemic vulnerabilities, we formulate the hedging process as a stochastic control problem and implement a Deep Hedging framework utilising Deep Reinforcement Learning (DRL). Optimised specifically for Expected Shortfall (ES), the model utilises Long Short-Term Memory (LSTM) layers to process multi-dimensional state vectors, including implied volatility skew and realised turbulence. Our empirical results demonstrate that this AI-optimised policy achieves a 35% reduction in hedging costs while simultaneously improving tail risk protection and draw-down resilience. Notably, the DRL agent exhibits anticipatory behaviour, transitioning from a reactive to a predictive paradigm by adjusting hedge positions prior to observable volatility spikes. These findings suggest that in structurally incomplete markets, optimal risk management has evolved from simple insurance into a process of continuous, regime-aware policy optimisation. This study provides a robust framework for institutional solvency in an era defined by non-linear correlations and rapid liquidity decay.
: A central feature of contemporary capital markets is their capacity to transfer and reallocate risk through options for hedging, speculation, and price discovery. As a result, option prices embed information about future uncertainty through valuation models that link observable market inputs to contingent payoffs. Traditional academic frameworks, most prominently the Black – Scholes model and its extensions, derive closed-form or semi-closed-form prices under idealized assumptions such as frictionless markets, continuous trading, log-normal asset returns, and constant or parametrically specified volatility dynamics. However, real-world markets exhibit volatility smiles and skews, price jumps, microstructure frictions, regime shifts, and heterogeneous data structures that violate these assumptions. In response, recent advances in financial technology have introduced data-intensive and computationally sophisticated approaches, including machine learning, deep learning, and high-performance simulation techniques, which infer pricing relationships non-parametrically from large panels of option prices and state variables. Option pricing can therefore be viewed as a trade-off among pricing accuracy, model stability, interpretability, arbitrage consistency, computational latency, and data requirements. Within this context, conventional structural models, data-driven methods, and hybrid frameworks that combine economic constraints with flexible learning architectures are increasingly evaluated for practical pricing and risk management applications.
Shu-Ya Lu· Proceedings of the 1st Inter...· 0 citations
Robust hedging valuation adjustment (HVA) is applied as a post-training valuation-adjustment layer that evaluates tracking-loss CVaR together with explicit funding and margin add-ons together with explicit funding and margin add-ons.
The rapid growth of retail investors in Indonesia, from 2.48 million in 2019 to over 20 million by 2025, underscores an urgent need for empirically grounded portfolio optimization frameworks adoptable into practical tools such as robo-advisory systems. This study applies the Markowitz Mean-Variance model to construct and evaluate an optimal stock portfolio from the LQ45 index over January 2022 to December 2025, a post-pandemic period characterized by predominantly adverse risk-adjusted returns. Using daily closing price data for 27 consistently listed LQ45 stocks (958 trading days) from the Indonesia Stock Exchange (IDX), with sample consistency verified through official BEI constituent evaluation announcements, this study constitutes an ex-post empirical analysis designed to isolate the mathematical efficacy of the Mean-Variance model under adverse market conditions. The analysis encompasses individual return and risk profiling, construction of a 27x27 covariance matrix, efficient frontier derivation via constrained quadratic optimization using Microsoft Excel Solver (GRG Nonlinear), and Sharpe ratio-based performance evaluation against a risk-free rate of 5.3281% per annum (average BI Rate 2022-2025). The core finding is that 19 of 27 sample stocks (70.4%) generated negative Sharpe ratios, confirming the inadequacy of undiversified single-stock strategies in adverse markets. In contrast, the tangency portfolio achieved a Sharpe ratio that materially surpasses all 27 individual stocks, establishing that quantitative portfolio optimization delivers superior risk-adjusted outcomes precisely when markets are most challenging. These results validate the enduring relevance of Modern Portfolio Theory in Indonesia's capital market and provide a transparent, replicable framework for investors and practitioners.
Irfan Andi Pramudya, Intan Shaferi· The International Conference...· 0 citations
This study analyzes the microstructural mechanisms through which the rapidly expanding single-stock leveraged ETFs in the Korean capital market impede the price discovery function and amplify endogenous volatility. Based on a dynamic simulation utilizing the actual market scales of large-cap semiconductor stocks, the results demonstrate that mechanical, pro-cyclical rebalancing concentrated at the market-on-close (MOC) induces directional distortion, systematically driving asset prices away from their fundamental values depending on market conditions. In particular, this study provides evidence that as the assets under management (AUM) of these linked products expand, the liquidity breakdown threshold of the limit order book declines steeply. Consequently, even minor illiquidity frictionscan cause mechanical selling pressure to escalate directly into tail risk. Drawing on these findings, this study offers policy implications to enhance macroprudential stability and prevent the transmission of microstructural risks into systemic risks. Specifically, we propose the introduction of dynamic AUM caps, the normalization of creation fees to mitigate structural conflicts of interest among Authorized Participants (APs), and restrictions on listing ultra-high leveraged products.
Sun-Joong Yoon· Korean Journal of Financial...· 0 citations
Structured retail products are unsecured bonds subject to the default risk of the issuer. We analyze the price‐setting policy of issuers with respect to this default risk. Using a long‐term data set of discount certificates in the German market, we apply a time series IVX‐approach to find that (i) quoted prices do depend on issuer default risk, but (ii) this dependency is under‐proportional. Hence, retail investors are only partially compensated for bearing issuer default risk. A long‐term analysis covering the global financial crisis, the European debt crisis, and the succeeding calm period, as well as supporting evidence from the coronavirus crisis, provides patterns consistent with a fading attention hypothesis: When default risk has left the focus of retail investors, they are no longer compensated for it, even if it becomes substantial, as in the early months of the coronavirus crisis.
R. Baule, Falk Jensen· Journal of futures markets· 0 citations
In the context of normalized volatility in the A-share market, traditional VaR models are unable to effectively capture the tail risk of extreme market conditions, while Expected Shortfall (ES) can make up for this deficiency. This paper selects 12 A-shares from two equally weighted stock portfolios within and outside the CSI 300 index, with a sample period from May 2022 to April 2026. It uses three methods—historical simulation, parametric method (normal), and GARCH (1,1)-t—to estimate VaR and ES, and conducts backtesting using the Kupiec POFF test, the Christoffersen conditional coverage test, and the Acerbi-Székely Z2 test. The results show that GARCH (1,1)-t can more accurately characterize tail risk at a 99% confidence level. The historical simulation method is generally robust, while the normal parameter method tends to underestimate systematic risk. ES is greater than VaR in all scenarios, which verifies its stronger ability to capture extreme losses. The conclusion remains unchanged after replacing the confidence level and portfolio weights. This paper recommends that A-share investors and regulatory agencies use ES as an important supplementary indicator to VaR, and prioritize the use of GARCH-t or historical simulation methods for risk measurement.
Yuhui Gao· Advances in Economics, Manag...· 0 citations