Simon Hirsch, Florian Ziel
Apr 21, 2026·q-fin.ST·PDF Electricity price forecasting supports decision-making in energy markets and asset operation. Probabilistic forecasts are increasingly adopted to explicitly quantify uncertainty, typically issued as quantile predictions or ensembles of the full predictive distribution. However, how improvements in statistical forecast quality translate into economic value remains unclear. Battery storage arbitrage in day-ahead markets is a popular application-based benchmark for this purpose. We analyze quantile-based trading strategies (QBTS) and identify two critical flaws: they do not incentivize honest probabilistic forecasting and they ignore the intertemporal dependence structure of electricity prices. We therefore frame battery optimization as a stochastic program based on fully probabilistic forecasts and examine decision quality measurement for risk-neutral and risk-averse settings under different uncertainty models. Our discussion touches both sides of the coin: How reliable is the economic evaluation of forecasting models though (simplified) application studies - and how do improvements in statistical forecast quality for stochastic programs relate to the decision-quality and economic performance? We provide theoretical justification and empirical evidence from a case study on the German electricity market. Our results highlight the pitfalls of ranking forecasting models through battery trading strategies. We conclude with implications for evaluation practice and directions for future research in application-based forecast assessment.
Yikuan Huang, Zheqi Fan, Kaiqi Hu, Yifan Ye
Apr 21, 2026·q-fin.PM·PDF Text-based financial networks are increasingly used to study cross-stock return predictability. A common approach constructs links from similarities in firms' disclosure embeddings, but such networks often contain spurious edges because textual proximity does not necessarily imply economic connection. We propose a two-stage framework that first builds a sparse candidate graph from 10-K embeddings and then uses a large language model to classify and filter candidate edges according to their economic relations. The refined graph is used to aggregate pair-level mean-reversion signals into stock-level trading signals with relation-aware and distance-based weights. In a backtest on S&P 500 constituents from 2011 to 2019, LLM-based edge filtering improves the long-short Sharpe ratio from 0.742 to 0.820 and reduces maximum drawdown from $-$10.47% to $-$7.85%. These results suggest that LLM-based reasoning can improve the economic fidelity of text-derived financial networks and strengthen cross-stock predictability.
Kundan Mukhia, Imran Ansari, Md. Nurujjaman
Apr 21, 2026·q-fin.ST·PDF We identify a robust structural signature of stock markets during exogenous shock events by analyzing collective return dynamics across G5 countries. Using Random Matrix Theory, we introduce the complexity gap, defined as the difference between the normalized largest eigenvalue and the average pairwise correlation, to quantify changes in market structure. This measure reveals a consistent three-phase pattern across multiple shocks, including the 2025 U.S. tariff event, the COVID-19 crisis, and country-specific shocks in Japan and China during 2024. Before a shock, markets show a positive complexity gap, reflecting a rich structure with multiple interacting factors. During shocks, the gap collapses to near zero, signaling strong synchronization under a single dominant mode. Post-shock recovery follows a nonmonotonic path: an initial widening (a false recovery), a temporary recollapse, and final sustained restoration. This pattern holds at both market and sector levels and across global and local shocks. Ordinal entropy analysis confirms the same sequence of collapse and false recovery in directional diversity. We further demonstrate that lower complexity gap values predict higher future portfolio volatility, especially after shocks, establishing its value as a state-dependent risk indicator. For investors, initial gap widening may mislead, while sustained widening signals genuine structural stabilization. These findings reveal a robust structural signature governing financial market dynamics during crisis and recovery periods.
George Fatouros, Kostas Metaxas
Apr 19, 2026·q-fin.PM·PDF We present the first portfolio-level validation of MarketSenseAI, a deployed multi-agent LLM equity system. All signals are generated live at each observation date, eliminating look-ahead bias. The system routes four specialist agents (News, Fundamentals, Dynamics, and Macro) through a synthesis agent that issues a monthly equity thesis and recommendation for each stock in its coverage universe, and we ask two questions: do its buy recommendations add value over both passive benchmarks and random selection, and what does the internal agent structure reveal about the source of the edge? On the S&P 500 cohort (19 months) the strong-buy equal-weight portfolio earns +2.18%/month against a passive equal-weight benchmark of +1.15% (approximating RSP), a +25.2% compound excess, and ranks at the 99.7th percentile of 10,000 Monte Carlo portfolios (p=0.003). The S&P 100 cohort (35 months) delivers a +30.5% compound excess over EQWL with consistent direction but formal significance not reached, limited by the small average selection of ~10 stocks per month. Non-negative least-squares projection of thesis embeddings onto agent embeddings reveals an adaptive-integration mechanism. Agent contributions rotate with market regime (Fundamentals leads on S&P 500, Macro on S&P 100, Dynamics acts as an episodic momentum signal) and this agent rotation moves in lockstep with both the sector composition of strong-buy selections and identifiable macro-calendar events, three independent views of the same underlying adaptation. The recommendation's cross-sectional Information Coefficient is statistically significant on S&P 500 (ICIR=+0.489, p=0.024). These results suggest that multi-agent LLM equity systems can identify sources of alpha beyond what classical factor models capture, and that the buy signal functions as an effective universe-filter that can sit upstream of any portfolio-construction process.
Haibin Jiao
Apr 18, 2026·q-fin.ST·PDF Shanghai Composite Index prediction has become a hot issue for many investors and academic researchers. Deep learning models are widely applied in multivariate time series forecasting, including recurrent neural networks (RNN), convolutional neural networks (CNN), and transformers. Specifically, the Transformer encoder, with its unique attention mechanism and parallel processing capabilities, has become an important tool in time series prediction, and has an advantage in dealing with long sequence dependencies and multivariate data correlations. Drawing on the strengths of various models, we propose the CNN-Transformer-LSTM Networks (CTLNet). This paper explores the application of CTLNet for Shanghai Composite Index prediction and the comparative experiments show that the proposed model outperforms state-of-the-art baselines.
Sotirios D. Nikolopoulos
Apr 16, 2026·q-fin.ST·PDF Adaptive specification search generates statistically significant backtests even under martingale-difference nulls. We introduce a falsification audit testing complete predictive workflows against synthetic reference classes, including zero-predictability environments and microstructure placebos. Workflows generating significant walk-forward evidence in these environments are falsified. For passing workflows, we quantify selection-induced performance inflation using an absolute magnitude gap linking optimized in-sample evidence to disjoint walk-forward realizations, adjusted for effective multiplicity. Simulations validate extreme-value scaling under correlated searches and demonstrate detection power under genuine structure. Empirical case studies confirm that many apparent findings represent methodological artifacts rather than genuine predictability.
Arshia Ghasemi, Siqi Shao, R. A. Serota
Apr 16, 2026·q-fin.ST·PDF We analyze historic S&P500 multi-day returns: from daily returns to those accumulated over up to ten days. Despite symmetry breaking between gains and losses in the distribution of returns, resulting in its positive mean and negative skew, realized variance (volatility squared) exhibits remarkably good linear dependence on the number of days of accumulation. Mean of the distribution also shows near perfect linear dependence as well. We analyze this phenomenon both analytically and numerically using a modified Jones-Faddy skew t-distribution.
Dhruvin Dungrani, Disha Dungrani
In computational paralinguistics, detecting cognitive load and deception from speech signals is a heavily researched domain. Recent efforts have attempted to apply these acoustic frameworks to corporate earnings calls to predict catastrophic stock market volatility. In this study, we empirically investigate the limits of acoustic feature extraction (pitch, jitter, and hesitation) when applied to highly trained speakers in in-the-wild teleconference environments. Utilizing a two-stream late-fusion architecture, we contrast an acoustic-based stream with a baseline Natural Language Processing (NLP) stream. The isolated NLP model achieved a recall of 66.25% for tail-risk downside events. Surprisingly, integrating acoustic features via late fusion significantly degraded performance, reducing recall to 47.08%. We identify this degradation as Acoustic Camouflage, where media-trained vocal regulation introduces contradictory noise that disrupts multimodal meta-learners. We present these findings as a boundary condition for speech processing applications in high-stakes financial forecasting.
Vygintas Gontis, Lesya Kolinets
Apr 13, 2026·q-fin.ST·PDF The long-run convergence of developing economies toward advanced countries exhibits robust empirical regularities, yet the mechanisms underlying technological diffusion remain insufficiently specified in standard growth models. In this paper, we extend the neoclassical framework by introducing a micro-founded mechanism of technological transfer as a driver of total factor productivity. Rather than treating technological progress as exogenous or purely innovation-driven, we model productivity growth as a process of adopting existing technologies from the global frontier. The diffusion process is described using a herding-type interaction mechanism, in which agents transition from non-adopters to adopters under the combined influence of individual incentives and peer effects. This approach yields a tractable aggregate representation of TFP dynamics characterized by nonlinear convergence toward a moving technological frontier. We derive an explicit analytical solution and provide an interpretation of model parameters in terms of initial productivity, convergence limits, and diffusion speed. The model is evaluated using OECD productivity data for Central and Eastern European economies.
Tenghan Zhong
Apr 12, 2026·q-fin.ST·PDF Volatility forecasting becomes challenging when market conditions shift and model performance varies across market states. Motivated by this instability, we develop a risk-sensitive specialist routing framework for ETF volatility forecasting. The framework uses online risk-sensitive evaluation and state-dependent gating to combine different forecasting specialists across calm and stressed market states. Using a daily panel of six ETFs under a rolling walk-forward design, we find that the strongest forecaster is regime-dependent rather than stable across all states. Relative to the rolling-best baseline, the proposed routing framework reduces high-volatility forecast loss by about 24% and underprediction loss by about 22%. These results suggest that specialist routing provides a practical forecasting architecture that adapts to changing market conditions.
Oleg Roshka
On a 93-actor quarterly panel mixing macro indicators, institutional data, and firm-level investment ratios, global factor augmentation degrades prediction for actor subgroups whose dynamics are misrepresented by the shared basis. A two-stage architecture -- global pooled AR(1) for shared persistence, block-specific local models for residual dynamics -- improves full-panel out-of-sample $R^2$ from 0.630 to 0.677 ($Δ= +0.047$, CI $[+0.036, +0.058]$, 10/10 windows, placebo $p \leq 0.001$). A held-out decade test -- block partition frozen on 2005--2014 data, evaluated on unseen 2015--2024 windows -- confirms the gain ($Δ= +0.050$, 10/10). Dropping the tech/health block eliminates roughly 72\% of the gain, making it the primary driver; rank-matched decomposition confirms this reflects a genuine cross-sector co-movement factor, not a rank-capacity artefact. Among the linear estimators tested, the gain is architectural rather than methodological; per-actor gradient boosting with the same block decomposition ($R^2 = 0.657$) does not close the gap, showing the advantage combines block-specific estimation with low-rank factor extraction. The gain arises only on heterogeneous mixed-type panels -- not on homogeneous firm-only panels -- identifying data-type heterogeneity as the operative condition. The result survives recursive macro normalisation ($+0.048$), a one-quarter filing-lag correction ($+0.038$, 10/10), and a stratified placebo that fixes the macro/firm data-type split and permutes only firm-sector assignments ($z = 7.25$, $p \leq 0.001$).
Ana Isabel Castillo Pereda
Apr 10, 2026·q-fin.ST·PDF This study extends the Gai-Kapadia framework, originally developed for interbank contagion, to assess systemic risk and default cascades in global equity markets. We analyze a 30 asset network comprising Brazilian and developed market equities over the period 2015-2026, constructing exposure based financial networks from price co-movements. Threshold filtering (theta = 0.3 and theta = 0.5) is applied to isolate significant interconnections. Cascade dynamics are analyzed through a combination of deterministic propagation and stochastic Monte Carlo simulations (n = 1000) under varying shock intensities. The results show that the system exhibits strong global resilience, with a negligible probability of large scale failure, while maintaining localized vulnerability within highly clustered subnetworks. In particular, shocks lead to an average of 1.0 failed asset for single shocks and 2.0 for simultaneous shocks, indicating limited propagation below a critical threshold. Network analysis reveals a clear structural asymmetry: Brazilian assets display high clustering (Ci approx 0.8-1.0) and dense connectivity, which amplifies local shock propagation, whereas developed market assets exhibit lower connectivity (Ci approx 0.2-0.5), limiting systemic spread. Tail risk analysis, based on empirical CCDF and Hill estimators, confirms the presence of heavy tailed loss distributions, particularly in emerging markets, reinforcing their exposure to extreme events. These findings demonstrate that systemic risk arises from the interaction between network topology and tail behavior, rather than from isolated asset characteristics. The proposed framework provides a scalable and empirically grounded approach for stress testing and systemic risk assessment, offering relevant insights for regulators and portfolio managers in increasingly interconnected financial markets.
Tenghan Zhong, Keyuan Wu
Daily ETF risk monitoring can become unreliable when market data quality degrades, market conditions shift, or predictive performance becomes unstable. This paper develops a reliability-aware risk monitoring service for next-day tail-risk surveillance. The proposed framework combines service-time quality checks, lower-tail prediction, uncertainty scoring, and risk-aware adjustment of the tail-risk estimate. We evaluate the system on a daily panel of multiple ETFs augmented with VIX and yield-curve information under a rolling walk-forward design. Empirically, the framework improves tail-risk monitoring, especially during stressed periods, while remaining reliable under simulated input degradation.
Marina Palaisti
This paper develops a copula-based time-series framework for modelling sovereign credit rating activity and its dependence dynamics, with extensions incorporating climate risk. We introduce a mixed-difference transformation that maps discrete annual counts of sovereign rating actions into a continuous domain, enabling flexible copula modelling. Building on a MAG(1) copula process, we extend the framework to a MAGMAR(1,1) specification combining moving-aggregate and autoregressive dependence, and establish consistency and asymptotic normality of the associated maximum likelihood estimators. The empirical analysis uses a multi-agency panel of sovereign ratings and country-level carbon intensity, aggregated to an annual measure of global rating activity. Results reveal strong nonlinear dependence and pronounced clustering of high-activity years, with the Gumbel MAGMAR(1,1) specification delivering the strongest empirical performance among the models considered, while standard Markov copulas and Poisson count models perform substantially worse. Climate covariates improve marginal models but do not materially enhance dependence dynamics, suggesting limited incremental explanatory power of the chosen aggregate climate proxy. The results highlight the value of parsimonious copula-based models for sovereign migration risk and stress testing.
Alexandre Alouadi, Grégoire Loeper, Célian Marsala, Othmane Mazhar, Huyên Pham
We study the problem of generating synthetic time series that reproduce both marginal distributions and temporal dynamics, a central challenge in financial machine learning. Existing approaches typically fail to jointly model drift and stochastic volatility, as diffusion-based methods fix the volatility while martingale transport models ignore drift. We introduce the Schrödinger-Bass Bridge for Time Series (SBBTS), a unified framework that extends the Schrödinger-Bass formulation to multi-step time series. The method constructs a diffusion process that jointly calibrates drift and volatility and admits a tractable decomposition into conditional transport problems, enabling efficient learning. Numerical experiments on the Heston model demonstrate that SBBTS accurately recovers stochastic volatility and correlation parameters that prior SchrödingerBridge methods fail to capture. Applied to S&P 500 data, SBBTS-generated synthetic time series consistently improve downstream forecasting performance when used for data augmentation, yielding higher classification accuracy and Sharpe ratio compared to real-data-only training. These results show that SBBTS provides a practical and effective framework for realistic time series generation and data augmentation in financial applications.
Masahiro Kato, Kei Nakagawa
Financial statement auditing is conducted under a risk-based evidence approach to obtain reasonable assurance. In practice, auditors often perform additional sampling or related procedures when an initial sample does not provide a sufficient basis for a conclusion. Across jurisdictions, current standards and practice manuals acknowledge such extensions, while the statistical design of sequential audit procedures has not been fully explored. This study formulates audit sampling with additional, sequentially collected items as a sequential testing problem for a finite population under sampling without replacement. We define null and alternative hypotheses in terms of a tolerable deviation rate, specify stopping and decision rules, and formulate exact sequential boundary conditions in terms of finite-population error probabilities. For practical implementation, we calibrate those boundaries by Monte Carlo simulation at least-favorable deviation rates. The exact design yields ex ante control of decision error probabilities, and the simulation-based implementation approximates that design while allowing the computation of expected stopping times. The framework is most naturally suited to attribute auditing and deviation-rate auditing, especially tests of controls, and it can be extended to one-sided, two-stage, and truncated designs.
Daniel Bloch
This paper introduces a novel generative framework for synthesising forward-looking, càdlàg stochastic trajectories that are sequentially consistent with time-evolving path-law proxies, thereby incorporating anticipated structural breaks, regime shifts, and non-autonomous dynamics. By framing path synthesis as a sequential matching problem on restricted Skorokhod manifolds, we develop the \textit{Anticipatory Neural Jump-Diffusion} (ANJD) flow, a generative mechanism that effectively inverts the time-extended Marcus-sense signature. Central to this approach is the Anticipatory Variance-Normalised Signature Geometry (AVNSG), a time-evolving precision operator that performs dynamic spectral whitening on the signature manifold to ensure contractivity during volatile regime shifts and discrete aleatoric shocks. We provide a rigorous theoretical analysis demonstrating that the joint generative flow constitutes an infinitesimal steepest descent direction for the Maximum Mean Discrepancy functional relative to a moving target proxy. Furthermore, we establish statistical generalisation bounds within the restricted path-space and analyse the Rademacher complexity of the whitened signature functionals to characterise the expressive power of the model under heavy-tailed innovations. The framework is implemented via a scalable numerical scheme involving Nyström-compressed score-matching and an anticipatory hybrid Euler-Maruyama-Marcus integration scheme. Our results demonstrate that the proposed method captures the non-commutative moments and high-order stochastic texture of complex, discontinuous path-laws with high computational efficiency.
Daniel Bloch
This paper introduces Anticipatory Reinforcement Learning (ARL), a novel framework designed to bridge the gap between non-Markovian decision processes and classical reinforcement learning architectures, specifically under the constraint of a single observed trajectory. In environments characterised by jump-diffusions and structural breaks, traditional state-based methods often fail to capture the essential path-dependent geometry required for accurate foresight. We resolve this by lifting the state space into a signature-augmented manifold, where the history of the process is embedded as a dynamical coordinate. By utilising a self-consistent field approach, the agent maintains an anticipated proxy of the future path-law, allowing for a deterministic evaluation of expected returns. This transition from stochastic branching to a single-pass linear evaluation significantly reduces computational complexity and variance. We prove that this framework preserves fundamental contraction properties and ensures stable generalisation even in the presence of heavy-tailed noise. Our results demonstrate that by grounding reinforcement learning in the topological features of path-space, agents can achieve proactive risk management and superior policy stability in highly volatile, continuous-time environments.
Tenghan Zhong
Short-horizon risk control matters for hedging and capital allocation. Yet existing Value-at-Risk studies rarely address standardized option books or the next-day valuation frictions that arise in derivatives data. This paper develops a framework for tail-risk control in standardized option books. The analysis focuses on the next-day realized loss and combines a base conditional quantile forecast with sequential conformal recalibration for adaptive Value-at-Risk control. This design addresses two central difficulties: unstable tail-risk forecasts under changing market conditions and the practical challenge of next-day valuation when exact same-contract quotes are unavailable. It also preserves economic interpretability through standardized construction and spot hedging when needed. Using SPX option data from 2018 to 2025, we show that the uncalibrated base model systematically underestimates downside risk across multiple standardized books. Sequential recalibration removes much of this shortfall, brings exceedance rates closer to target, and improves rolling-window tail stability, with the largest gains in the books where the raw forecast is most vulnerable. The paper also provides an approximate one-step exceedance-control result for the sequential recalibration rule and quantifies the error introduced by next-day marking.
Luigi Caputi, Nicholas Meadows
In this work we evaluate the performance of three classes of methods for detecting financial anomalies: topological data analysis (TDA), principal component analyis (PCA), and Neural Network-based approaches. We apply these methods to the TSX-60 data to identify major financial stress events in the Canadian stock market. We show how neural network-based methods (such as GlocalKD and One-Shot GIN(E)) and TDA methods achieve the strongest performance. The effectiveness of TDA in detecting financial anomalies suggests that global topological properties are meaningful in distinguishing financial stress events.