Can We Reliably Predict the Fed’s Next Move? A Multi-Modal Approach to U.S. Monetary Policy Forecasting ArXiv ID: 2506.22763 “View on arXiv” Authors: Fiona Xiao Jingyi, Lili Liu Abstract Forecasting central bank policy decisions remains a persistent challenge for investors, financial institutions, and policymakers due to the wide-reaching impact of monetary actions. In particular, anticipating shifts in the U.S. federal funds rate is vital for risk management and trading strategies. Traditional methods relying only on structured macroeconomic indicators often fall short in capturing the forward-looking cues embedded in central bank communications. This study examines whether predictive accuracy can be enhanced by integrating structured data with unstructured textual signals from Federal Reserve communications. We adopt a multi-modal framework, comparing traditional machine learning models, transformer-based language models, and deep learning architectures in both unimodal and hybrid settings. Our results show that hybrid models consistently outperform unimodal baselines. The best performance is achieved by combining TF-IDF features of FOMC texts with economic indicators in an XGBoost classifier, reaching a test AUC of 0.83. FinBERT-based sentiment features marginally improve ranking but perform worse in classification, especially under class imbalance. SHAP analysis reveals that sparse, interpretable features align more closely with policy-relevant signals. These findings underscore the importance of integrating textual and structured signals transparently. For monetary policy forecasting, simpler hybrid models can offer both accuracy and interpretability, delivering actionable insights for researchers and decision-makers. ...

Currents Beneath Stability: A Stochastic Framework for Exchange Rate Instability Using Kramers Moyal Expansion ArXiv ID: 2507.01989 “View on arXiv” Authors: Yazdan Babazadeh Maghsoodlo, Amin Safaeesirat Abstract Understanding the stochastic behavior of currency exchange rates is critical for assessing financial stability and anticipating market transitions. In this study, we investigate the empirical dynamics of the USD exchange rate in three economies, including Iran, Turkey, and Sri Lanka, through the lens of the Kramers-Moyal expansion and Fokker-Planck formalism. Using log-return data, we confirm the Markovian nature of the exchange rate fluctuations, enabling us to model the system with a second-order Fokker-Planck equation. The inferred Langevin coefficients reveal a stabilizing linear drift and a nonlinear, return-dependent diffusion term, reflecting both regulatory effects and underlying volatility. A rolling-window estimation of these coefficients, paired with structural breakpoint detection, uncovers regime shifts that align with major political and economic events, offering insight into the hidden dynamics of currency instability. This framework provides a robust foundation for detecting latent transitions and modeling risk in complex financial systems. ...

Potential Customer Lifetime Value in Financial Institutions: The Usage Of Open Banking Data to Improve CLV Estimation ArXiv ID: 2506.22711 “View on arXiv” Authors: João B. G. de Brito, Rodrigo Heldt, Cleo S. Silveira, Matthias Bogaert, Guilherme B. Bucco, Fernando B. Luce, João L. Becker, Filipe J. Zabala, Michel J. Anzanello Abstract Financial institutions increasingly adopt customer-centric strategies to enhance profitability and build long-term relationships. While Customer Lifetime Value (CLV) is a core metric, its calculations often rely solely on single-entity data, missing insights from customer activities across multiple firms. This study introduces the Potential Customer Lifetime Value (PCLV) framework, leveraging Open Banking (OB) data to estimate customer value comprehensively. We predict retention probability and estimate Potential Contribution Margins (PCM) from competitor data, enabling PCLV calculation. Results show that OB data can be used to estimate PCLV per competitor, indicating a potential upside of 21.06% over the Actual CLV. PCLV offers a strategic tool for managers to strengthen competitiveness by leveraging OB data and boost profitability by driving marketing efforts at the individual customer level to increase the Actual CLV. ...

SABR-Informed Multitask Gaussian Process: A Synthetic-to-Real Framework for Implied Volatility Surface Construction ArXiv ID: 2506.22888 “View on arXiv” Authors: Jirong Zhuang, Xuan Wu Abstract Constructing the Implied Volatility Surface (IVS) is a challenging task in quantitative finance due to the complexity of real markets and the sparsity of market data. Structural models like Stochastic Alpha Beta Rho (SABR) model offer interpretability and theoretical consistency but lack flexibility, while purely data-driven methods such as Gaussian Process regression can struggle with sparse data. We introduce SABR-Informed Multi-Task Gaussian Process (SABR-MTGP), treating IVS construction as a multi-task learning problem. Our method uses a dense synthetic dataset from a calibrated SABR model as a source task to inform the construction based on sparse market data (the target task). The MTGP framework captures task correlation and transfers structural information adaptively, improving predictions particularly in data-scarce regions. Experiments using Heston-generated ground truth data under various market conditions show that SABR-MTGP outperforms both standard Gaussian process regression and SABR across different maturities. Furthermore, an application to real SPX market data demonstrates the method’s practical applicability and its ability to produce stable and realistic surfaces. This confirms our method balances structural guidance from SABR with the flexibility needed for market data. ...

Deep Hedging to Manage Tail Risk ArXiv ID: 2506.22611 “View on arXiv” Authors: Yuming Ma Abstract Extending Buehler et al.’s 2019 Deep Hedging paradigm, we innovatively employ deep neural networks to parameterize convex-risk minimization (CVaR/ES) for the portfolio tail-risk hedging problem. Through comprehensive numerical experiments on crisis-era bootstrap market simulators – customizable with transaction costs, risk budgets, liquidity constraints, and market impact – our end-to-end framework not only achieves significant one-day 99% CVaR reduction but also yields practical insights into friction-aware strategy adaptation, demonstrating robustness and operational viability in realistic markets. ...

Optimal Benchmark Design under Costly Manipulation ArXiv ID: 2506.22142 “View on arXiv” Authors: Ángel Hernando-Veciana Abstract Price benchmarks are used to incorporate market price trends into contracts, but their use can create opportunities for manipulation by parties involved in the contract. This paper examines this issue using a realistic and tractable model inspired by smart contracts on blockchains like Ethereum. In our model, manipulation costs depend on two factors: the magnitude of adjustments to individual prices (variable costs) and the number of prices adjusted (fixed costs). We find that a weighted mean is the optimal benchmark when fixed costs are negligible, while the median is optimal when variable costs are negligible. In cases where both fixed and variable costs are significant, the optimal benchmark can be implemented as a trimmed mean, with the degree of trimming increasing as fixed costs become more important relative to variable costs. Furthermore, we show that the optimal weights for a mean-based benchmark are proportional to the marginal manipulation costs, whereas the median remains optimal without weighting, even when fixed costs differ across prices. ...

Comparing Bitcoin and Ethereum tail behavior via Q-Q analysis of cryptocurrency returns ArXiv ID: 2507.01983 “View on arXiv” Authors: A. H. Nzokem Abstract The cryptocurrency market presents both significant investment opportunities and higher risks relative to traditional financial assets. This study examines the tail behavior of daily returns for two leading cryptocurrencies, Bitcoin and Ethereum, using seven-parameter estimates from prior research, which applied the Generalized Tempered Stable (GTS) distribution. Quantile-quantile (Q-Q) plots against the Normal distribution reveal that both assets exhibit heavy-tailed return distributions. However, Ethereum consistently shows a greater frequency of extreme values than would be expected under its Bitcoin-modeled counterpart, indicating more pronounced tail risk. ...

From On-chain to Macro: Assessing the Importance of Data Source Diversity in Cryptocurrency Market Forecasting ArXiv ID: 2506.21246 “View on arXiv” Authors: Giorgos Demosthenous, Chryssis Georgiou, Eliada Polydorou Abstract This study investigates the impact of data source diversity on the performance of cryptocurrency forecasting models by integrating various data categories, including technical indicators, on-chain metrics, sentiment and interest metrics, traditional market indices, and macroeconomic indicators. We introduce the Crypto100 index, representing the top 100 cryptocurrencies by market capitalization, and propose a novel feature reduction algorithm to identify the most impactful and resilient features from diverse data sources. Our comprehensive experiments demonstrate that data source diversity significantly enhances the predictive performance of forecasting models across different time horizons. Key findings include the paramount importance of on-chain metrics for both short-term and long-term predictions, the growing relevance of traditional market indices and macroeconomic indicators for longer-term forecasts, and substantial improvements in model accuracy when diverse data sources are utilized. These insights help demystify the short-term and long-term driving factors of the cryptocurrency market and lay the groundwork for developing more accurate and resilient forecasting models. ...

On the hidden costs of passive investing ArXiv ID: 2506.21775 “View on arXiv” Authors: Iro Tasitsiomi Abstract Passive investing has gained immense popularity due to its low fees and the perceived simplicity of focusing on zero tracking error, rather than security selection. However, our analysis shows that the passive (zero tracking error) approach of waiting until the market close on the day of index reconstitution to purchase a stock (that was announced days earlier as an upcoming addition) results in costs amounting to hundreds of basis points compared to strategies that involve gradually acquiring a small portion of the required shares in advance with minimal additional tracking errors. In addition, we show that under all scenarios analyzed, a trader who builds a small inventory post-announcement and provides liquidity at the reconstitution event can consistently earn several hundreds of basis points in profit and often much more, assuming minimal risk. ...

Quantum Reinforcement Learning Trading Agent for Sector Rotation in the Taiwan Stock Market ArXiv ID: 2506.20930 “View on arXiv” Authors: Chi-Sheng Chen, Xinyu Zhang, Ya-Chuan Chen Abstract We propose a hybrid quantum-classical reinforcement learning framework for sector rotation in the Taiwan stock market. Our system employs Proximal Policy Optimization (PPO) as the backbone algorithm and integrates both classical architectures (LSTM, Transformer) and quantum-enhanced models (QNN, QRWKV, QASA) as policy and value networks. An automated feature engineering pipeline extracts financial indicators from capital share data to ensure consistent model input across all configurations. Empirical backtesting reveals a key finding: although quantum-enhanced models consistently achieve higher training rewards, they underperform classical models in real-world investment metrics such as cumulative return and Sharpe ratio. This discrepancy highlights a core challenge in applying reinforcement learning to financial domains – namely, the mismatch between proxy reward signals and true investment objectives. Our analysis suggests that current reward designs may incentivize overfitting to short-term volatility rather than optimizing risk-adjusted returns. This issue is compounded by the inherent expressiveness and optimization instability of quantum circuits under Noisy Intermediate-Scale Quantum (NISQ) constraints. We discuss the implications of this reward-performance gap and propose directions for future improvement, including reward shaping, model regularization, and validation-based early stopping. Our work offers a reproducible benchmark and critical insights into the practical challenges of deploying quantum reinforcement learning in real-world finance. ...