Forecasting

Modeling Hawkish-Dovish Latent Beliefs in Multi-Agent Debate-Based LLMs for Monetary Policy Decision Classification ArXiv ID: 2511.02469 “View on arXiv” Authors: Kaito Takano, Masanori Hirano, Kei Nakagawa Abstract Accurately forecasting central bank policy decisions, particularly those of the Federal Open Market Committee(FOMC) has become increasingly important amid heightened economic uncertainty. While prior studies have used monetary policy texts to predict rate changes, most rely on static classification models that overlook the deliberative nature of policymaking. This study proposes a novel framework that structurally imitates the FOMC’s collective decision-making process by modeling multiple large language models(LLMs) as interacting agents. Each agent begins with a distinct initial belief and produces a prediction based on both qualitative policy texts and quantitative macroeconomic indicators. Through iterative rounds, agents revise their predictions by observing the outputs of others, simulating deliberation and consensus formation. To enhance interpretability, we introduce a latent variable representing each agent’s underlying belief(e.g., hawkish or dovish), and we theoretically demonstrate how this belief mediates the perception of input information and interaction dynamics. Empirical results show that this debate-based approach significantly outperforms standard LLMs-based baselines in prediction accuracy. Furthermore, the explicit modeling of beliefs provides insights into how individual perspectives and social influence shape collective policy forecasts. ...

Modeling and Forecasting Realized Volatility with Multivariate Fractional Brownian Motion ArXiv ID: 2504.15985 “View on arXiv” Authors: Unknown Abstract A multivariate fractional Brownian motion (mfBm) with component-wise Hurst exponents is used to model and forecast realized volatility. We investigate the interplay between correlation coefficients and Hurst exponents and propose a novel estimation method for all model parameters, establishing consistency and asymptotic normality of the estimators. Additionally, we develop a time-reversibility test, which is typically not rejected by real volatility data. When the data-generating process is a time-reversible mfBm, we derive optimal forecasting formulae and analyze their properties. A key insight is that an mfBm with different Hurst exponents and non-zero correlations can reduce forecasting errors compared to a one-dimensional model. Consistent with optimal forecasting theory, out-of-sample forecasts using the time-reversible mfBm show improvements over univariate fBm, particularly when the estimated Hurst exponents differ significantly. Empirical results demonstrate that mfBm-based forecasts outperform the (vector) HAR model. ...

Using quantile time series and historical simulation to forecast financial risk multiple steps ahead ArXiv ID: 2502.20978 “View on arXiv” Authors: Unknown Abstract A method for quantile-based, semi-parametric historical simulation estimation of multiple step ahead Value-at-Risk (VaR) and Expected Shortfall (ES) models is developed. It uses the quantile loss function, analogous to how the quasi-likelihood is employed by standard historical simulation methods. The returns data are scaled by the estimated quantile series, then resampling is employed to estimate the forecast distribution one and multiple steps ahead, allowing tail risk forecasting. The proposed method is applicable to any data or model where the relationship between VaR and ES does not change over time and can be extended to allow a measurement equation incorporating realized measures, thus including Realized GARCH and Realized CAViaR type models. Its finite sample properties, and its comparison with existing historical simulation methods, are evaluated via a simulation study. A forecasting study assesses the relative accuracy of the 1% and 2.5% VaR and ES one-day-ahead and ten-day-ahead forecasting results for the proposed class of models compared to several competitors. ...

Value of Information in the Mean-Square Case and its Application to the Analysis of Financial Time-Series Forecast ArXiv ID: 2410.01831 “View on arXiv” Authors: Unknown Abstract The advances and development of various machine learning techniques has lead to practical solutions in various areas of science, engineering, medicine and finance. The great choice of algorithms, their implementations and libraries has resulted in another challenge of selecting the right algorithm and tuning their parameters in order to achieve optimal or satisfactory performance in specific applications. Here we show how the value of information (V(I)) can be used in this task to guide the algorithm choice and parameter tuning process. After estimating the amount of Shannon’s mutual information between the predictor and response variables, V(I) can define theoretical upper bound of performance of any algorithm. The inverse function I(V) defines the lower frontier of the minimum amount of information required to achieve the desired performance. In this paper, we illustrate the value of information for the mean-square error minimization and apply it to forecasts of cryptocurrency log-returns. ...

Investment strategies based on forecasts are (almost) useless ArXiv ID: 2408.01772 “View on arXiv” Authors: Unknown Abstract Several studies on portfolio construction reveal that sensible strategies essentially yield the same results as their nonsensical inverted counterparts; moreover, random portfolios managed by Malkiel’s dart-throwing monkey would outperform the cap-weighted benchmark index. Forecasting the future development of stock returns is an important aspect of portfolio assessment. Similar to the ostensible arbitrariness of portfolio selection methods, it is shown that there is no substantial difference between the performances of best'' and trivial’’ forecasts - even under euphemistic model assumptions on the underlying price dynamics. A certain significance of a predictor is found only in the following special case: the best linear unbiased forecast is used, the planning horizon is small, and a critical relation is not satisfied. ...

Entropy corrected geometric Brownian motion ArXiv ID: 2403.06253 “View on arXiv” Authors: Unknown Abstract The geometric Brownian motion (GBM) is widely employed for modeling stochastic processes, yet its solutions are characterized by the log-normal distribution. This comprises predictive capabilities of GBM mainly in terms of forecasting applications. Here, entropy corrections to GBM are proposed to go beyond log-normality restrictions and better account for intricacies of real systems. It is shown that GBM solutions can be effectively refined by arguing that entropy is reduced when deterministic content of considered data increases. Notable improvements over conventional GBM are observed for several cases of non-log-normal distributions, ranging from a dice roll experiment to real world data. ...

Prediction Of Cryptocurrency Prices Using LSTM, SVM And Polynomial Regression ArXiv ID: 2403.03410 “View on arXiv” Authors: Unknown Abstract The rapid development of information technology, especially the Internet, has facilitated users with a quick and easy way to seek information. With these convenience offered by internet services, many individuals who initially invested in gold and precious metals are now shifting into digital investments in form of cryptocurrencies. However, investments in crypto coins are filled with uncertainties and fluctuation in daily basis. This risk posed as significant challenges for coin investors that could result in substantial investment losses. The uncertainty of the value of these crypto coins is a critical issue in the field of coin investment. Forecasting, is one of the methods used to predict the future value of these crypto coins. By utilizing the models of Long Short Term Memory, Support Vector Machine, and Polynomial Regression algorithm for forecasting, a performance comparison is conducted to determine which algorithm model is most suitable for predicting crypto currency prices. The mean square error is employed as a benchmark for the comparison. By applying those three constructed algorithm models, the Support Vector Machine uses a linear kernel to produce the smallest mean square error compared to the Long Short Term Memory and Polynomial Regression algorithm models, with a mean square error value of 0.02. Keywords: Cryptocurrency, Forecasting, Long Short Term Memory, Mean Square Error, Polynomial Regression, Support Vector Machine ...

Analyzing Currency Fluctuations: A Comparative Study of GARCH, EWMA, and IV Models for GBP/USD and EUR/GBP Pairs ArXiv ID: 2402.07435 “View on arXiv” Authors: Unknown Abstract In this study, we examine the fluctuation in the value of the Great Britain Pound (GBP). We focus particularly on its relationship with the United States Dollar (USD) and the Euro (EUR) currency pairs. Utilizing data from June 15, 2018, to June 15, 2023, we apply various mathematical models to assess their effectiveness in predicting the 20-day variation in the pairs’ daily returns. Our analysis involves the implementation of Exponentially Weighted Moving Average (EWMA), Generalized Autoregressive Conditional Heteroskedasticity (GARCH) models, and Implied Volatility (IV) models. To evaluate their performance, we compare the accuracy of their predictions using Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) metrics. We delve into the intricacies of GARCH models, examining their statistical characteristics when applied to the provided dataset. Our findings suggest the existence of asymmetric returns in the EUR/GBP pair, while such evidence is inconclusive for the GBP/USD pair. Additionally, we observe that GARCH-type models better fit the data when assuming residuals follow a standard t-distribution rather than a standard normal distribution. Furthermore, we investigate the efficacy of different forecasting techniques within GARCH-type models. Comparing rolling window forecasts to expanding window forecasts, we find no definitive superiority in either approach across the tested scenarios. Our experiments reveal that for the GBP/USD pair, the most accurate volatility forecasts stem from the utilization of GARCH models employing a rolling window methodology. Conversely, for the EUR/GBP pair, optimal forecasts are derived from GARCH models and Ordinary Least Squares (OLS) models incorporating the annualized implied volatility of the exchange rate as an independent variable. ...

Markowitz Portfolio Construction at Seventy ArXiv ID: 2401.05080 “View on arXiv” Authors: Unknown Abstract More than seventy years ago Harry Markowitz formulated portfolio construction as an optimization problem that trades off expected return and risk, defined as the standard deviation of the portfolio returns. Since then the method has been extended to include many practical constraints and objective terms, such as transaction cost or leverage limits. Despite several criticisms of Markowitz’s method, for example its sensitivity to poor forecasts of the return statistics, it has become the dominant quantitative method for portfolio construction in practice. In this article we describe an extension of Markowitz’s method that addresses many practical effects and gracefully handles the uncertainty inherent in return statistics forecasting. Like Markowitz’s original formulation, the extension is also a convex optimization problem, which can be solved with high reliability and speed. ...

Rough volatility: evidence from range volatility estimators ArXiv ID: 2312.01426 “View on arXiv” Authors: Unknown Abstract In Gatheral et al. 2018, first posted in 2014, volatility is characterized by fractional behavior with a Hurst exponent $H < 0.5$, challenging traditional views of volatility dynamics. Gatheral et al. demonstrated this using realized volatility measurements. Our study extends this analysis by employing range-based proxies to confirm their findings across a broader dataset and non-standard assets. Notably, we address the concern that rough volatility might be an artifact of microstructure noise in high-frequency return data. Our results reveal that log-volatility, estimated via range-based methods, behaves akin to fractional Brownian motion with an even lower $H$, below $0.1$. We also affirm the efficacy of the rough fractional stochastic volatility model (RFSV), finding that its predictive capability surpasses that of AR, HAR, and GARCH models in most scenarios. This work substantiates the intrinsic nature of rough volatility, independent of the microstructure noise often present in high-frequency financial data. ...