CBDC Stress Test in a Dual-Currency Setting ArXiv ID: 2511.13384 “View on arXiv” Authors: Catalin Dumitrescu Abstract This study explores the potential impact of introducing a Central Bank Digital Currency (CBDC) on financial stability in an emerging dual-currency economy (Romania), where the domestic currency (RON) coexists with the euro. It develops an integrated analytical framework combining econometrics, machine learning, and behavioural modelling. CBDC adoption probabilities are estimated using XGBoost and logistic regression models trained on behavioural and macro-financial indicators rather than survey data. Liquidity stress simulations assess how banks would respond to deposit withdrawals resulting from CBDC adoption, while VAR, MSVAR, and SVAR models capture the macro-financial transmission of liquidity shocks into credit contraction and changes in monetary conditions. The findings indicate that CBDC uptake (co-circulating Digital RON and Digital EUR) would be moderate at issuance, amounting to around EUR 1 billion, primarily driven by digital readiness and trust in the central bank. The study concludes that a non-remunerated, capped CBDC, designed primarily as a means of payment rather than a store of value, can be introduced without compromising financial stability. In dual currency economies, differentiated holding limits for domestic and foreign digital currencies (e.g., Digital RON versus Digital Euro) are crucial to prevent uncontrolled euroisation and preserve monetary sovereignty. A prudent design with moderate caps, non remuneration, and macroprudential coordination can transform CBDC into a digital liquidity buffer and a complementary monetary policy instrument that enhances resilience and inclusion rather than destabilising the financial system. ...

Market-Dependent Communication in Multi-Agent Alpha Generation ArXiv ID: 2511.13614 “View on arXiv” Authors: Jerick Shi, Burton Hollifield Abstract Multi-strategy hedge funds face a fundamental organizational choice: should analysts generating trading strategies communicate, and if so, how? We investigate this using 5-agent LLM-based trading systems across 450 experiments spanning 21 months, comparing five organizational structures from isolated baseline to collaborative and competitive conversation. We show that communication improves performance, but optimal communication design depends on market characteristics. Competitive conversation excels in volatile technology stocks, while collaborative conversation dominates stable general stocks. Finance stocks resist all communication interventions. Surprisingly, all structures, including isolated agents, converge to similar strategy alignments, challenging assumptions that transparency causes harmful diversity loss. Performance differences stem from behavioral mechanisms: competitive agents focus on stock-level allocation while collaborative agents develop technical frameworks. Conversation quality scores show zero correlation with returns. These findings demonstrate that optimal communication design must match market volatility characteristics, and sophisticated discussions don’t guarantee better performance. ...

Opportunity Cost in Insurance ArXiv ID: 2511.13959 “View on arXiv” Authors: Jan Maelger Abstract We develop a formalism for insurance profit optimisation for the in-force business constraint by regulatory and risk policy related requirements. This approach is applicable to Life, P&C and Reinsurance businesses and applies in all regulatory frameworks with a solvency requirement defined in the form of a solvency ratio, notably Solvency II and the Swiss Solvency Test. We identify the optimal asset allocation for profit maximisation within a pre-defined risk appetite and deduce the annual opportunity cost faced by the insurance company. ...

Stationary Distributions of the Mode-switching Chiarella Model ArXiv ID: 2511.13277 “View on arXiv” Authors: Jutta G. Kurth, Jean-Philippe Bouchaud Abstract We derive the stationary distribution in various regimes of the extended Chiarella model of financial markets. This model is a stochastic nonlinear dynamical system that encompasses dynamical competition between a (saturating) trending and a mean-reverting component. We find the so-called mispricing distribution and the trend distribution to be unimodal Gaussians in the small noise, small feedback limit. Slow trends yield Gaussian-cosh mispricing distributions that allow for a P-bifurcation: unimodality occurs when mean-reversion is fast, bimodality when it is slow. The critical point of this bifurcation is established and refutes previous ad-hoc reports and differs from the bifurcation condition of the dynamical system itself. For fast, weakly coupled trends, deploying the Furutsu-Novikov theorem reveals that the result is again unimodal Gaussian. For the same case with higher coupling we disprove another claim from the literature: bimodal trend distributions do not generally imply bimodal mispricing distributions. The latter becomes bimodal only for stronger trend feedback. The exact solution in this last regime remains unfortunately beyond our proficiency. ...

Statistical and economic evaluation of forecasts in electricity markets: beyond RMSE and MAE ArXiv ID: 2511.13616 “View on arXiv” Authors: Katarzyna Maciejowska, Arkadiusz Lipiecki, Bartosz Uniejewski Abstract In recent years, a rapid development of forecasting methods has led to an increase in the accuracy of predictions. In the literature, forecasts are typically evaluated using metrics such as Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). While appropriate for statistical assessment, these measures do not adequately reflect the economic value of forecasts. This study addresses the decision-making problem faced by a battery energy storage system, which must determine optimal charging and discharging times based on day-ahead electricity price forecasts. To explore the relationship between forecast accuracy and economic value, we generate a pool of 192 forecasts. These are evaluated using seven statistical metrics that go beyond RMSE and MAE, capturing various characteristics of the predictions and associated errors. We calculate the dynamic correlation between the statistical measures and gained profits to reveal that both RMSE and MAE are only weakly correlated with revenue. In contrast, measures that assess the alignment between predicted and actual daily price curves have a stronger relationship with profitability and are thus more effective for selecting optimal forecasts. ...

Cryptocurrency Portfolio Management with Reinforcement Learning: Soft Actor–Critic and Deep Deterministic Policy Gradient Algorithms ArXiv ID: 2511.20678 “View on arXiv” Authors: Kamal Paykan Abstract This paper proposes a reinforcement learning–based framework for cryptocurrency portfolio management using the Soft Actor–Critic (SAC) and Deep Deterministic Policy Gradient (DDPG) algorithms. Traditional portfolio optimization methods often struggle to adapt to the highly volatile and nonlinear dynamics of cryptocurrency markets. To address this, we design an agent that learns continuous trading actions directly from historical market data through interaction with a simulated trading environment. The agent optimizes portfolio weights to maximize cumulative returns while minimizing downside risk and transaction costs. Experimental evaluations on multiple cryptocurrencies demonstrate that the SAC and DDPG agents outperform baseline strategies such as equal-weighted and mean–variance portfolios. The SAC algorithm, with its entropy-regularized objective, shows greater stability and robustness in noisy market conditions compared to DDPG. These results highlight the potential of deep reinforcement learning for adaptive and data-driven portfolio management in cryptocurrency markets. ...

Discovery of a 13-Sharpe OOS Factor: Drift Regimes Unlock Hidden Cross-Sectional Predictability ArXiv ID: 2511.12490 “View on arXiv” Authors: Mainak Singha Abstract We document a high-performing cross-sectional equity factor that achieves out-of-sample Sharpe ratios above 13 through regime-conditional signal activation. The strategy combines value and short-term reversal signals only during stock-specific drift regimes, defined as periods when individual stocks show more than 60 percent positive days in trailing 63-day windows. Under these conditions, the factor delivers annualized returns of 158.6 percent with 12.0 percent volatility and a maximum drawdown of minus 11.9 percent. Using rigorous walk-forward validation across 20 years of S&P 500 data (2004 to 2024), we show performance roughly 13 times stronger than market benchmarks on a risk-adjusted basis, produced entirely out-of-sample with frozen parameters. The factor passes extensive robustness tests, including 1,000 randomization trials with p-values below 0.001, and maintains Sharpe ratios above 7 even under 30 percent parameter perturbations. Exposure to standard risk factors is negligible, with total R-squared values below 3 percent. We provide mechanistic evidence that drift regimes reshape market microstructure by amplifying behavioral biases, altering liquidity patterns, and creating conditions where cross-sectional price discovery becomes systematically exploitable. Conservative capacity estimates indicate deployable capital of 100 to 500 million dollars before noticeable performance degradation. ...

Impact by design: translating Lead times in flux into an R handbook with code ArXiv ID: 2511.12763 “View on arXiv” Authors: Harrison Katz Abstract This commentary translates the central ideas in Lead times in flux into a practice ready handbook in R. The original article measures change in the full distribution of booking lead times with a normalized L1 distance and tracks that divergence across months relative to year over year and to a fixed 2018 reference. It also provides a bound that links divergence and remaining horizon to the relative error of pickup forecasts. We implement these ideas end to end in R, using a minimal data schema and providing runnable scripts, simulated examples, and a prespecified evaluation plan. All results use synthetic data so the exposition is fully reproducible without reference to proprietary sources. ...

A Practical Machine Learning Approach for Dynamic Stock Recommendation ArXiv ID: 2511.12129 “View on arXiv” Authors: Hongyang Yang, Xiao-Yang Liu, Qingwei Wu Abstract Stock recommendation is vital to investment companies and investors. However, no single stock selection strategy will always win while analysts may not have enough time to check all S&P 500 stocks (the Standard & Poor’s 500). In this paper, we propose a practical scheme that recommends stocks from S&P 500 using machine learning. Our basic idea is to buy and hold the top 20% stocks dynamically. First, we select representative stock indicators with good explanatory power. Secondly, we take five frequently used machine learning methods, including linear regression, ridge regression, stepwise regression, random forest and generalized boosted regression, to model stock indicators and quarterly log-return in a rolling window. Thirdly, we choose the model with the lowest Mean Square Error in each period to rank stocks. Finally, we test the selected stocks by conducting portfolio allocation methods such as equally weighted, mean-variance, and minimum-variance. Our empirical results show that the proposed scheme outperforms the long-only strategy on the S&P 500 index in terms of Sharpe ratio and cumulative returns. This work is fully open-sourced at \href{“https://github.com/AI4Finance-Foundation/Dynamic-Stock-Recommendation-Machine_Learning-Published-Paper-IEEE"}{"GitHub"}. ...

Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy ArXiv ID: 2511.12120 “View on arXiv” Authors: Hongyang Yang, Xiao-Yang Liu, Shan Zhong, Anwar Walid Abstract Stock trading strategies play a critical role in investment. However, it is challenging to design a profitable strategy in a complex and dynamic stock market. In this paper, we propose an ensemble strategy that employs deep reinforcement schemes to learn a stock trading strategy by maximizing investment return. We train a deep reinforcement learning agent and obtain an ensemble trading strategy using three actor-critic based algorithms: Proximal Policy Optimization (PPO), Advantage Actor Critic (A2C), and Deep Deterministic Policy Gradient (DDPG). The ensemble strategy inherits and integrates the best features of the three algorithms, thereby robustly adjusting to different market situations. In order to avoid the large memory consumption in training networks with continuous action space, we employ a load-on-demand technique for processing very large data. We test our algorithms on the 30 Dow Jones stocks that have adequate liquidity. The performance of the trading agent with different reinforcement learning algorithms is evaluated and compared with both the Dow Jones Industrial Average index and the traditional min-variance portfolio allocation strategy. The proposed deep ensemble strategy is shown to outperform the three individual algorithms and two baselines in terms of the risk-adjusted return measured by the Sharpe ratio. This work is fully open-sourced at \href{“https://github.com/AI4Finance-Foundation/Deep-Reinforcement-Learning-for-Automated-Stock-Trading-Ensemble-Strategy-ICAIF-2020"}{"GitHub"}. ...