|
on Forecasting |
|
Issue of 2025–09–01
nineteen papers chosen by |
| By: | Grzegorz Dudek; Witold Orzeszko; Piotr Fiszeder |
| Abstract: | Cryptocurrency markets are characterized by extreme volatility, making accurate forecasts essential for effective risk management and informed trading strategies. Traditional deterministic (point) forecasting methods are inadequate for capturing the full spectrum of potential volatility outcomes, underscoring the importance of probabilistic approaches. To address this limitation, this paper introduces probabilistic forecasting methods that leverage point forecasts from a wide range of base models, including statistical (HAR, GARCH, ARFIMA) and machine learning (e.g. LASSO, SVR, MLP, Random Forest, LSTM) algorithms, to estimate conditional quantiles of cryptocurrency realized variance. To the best of our knowledge, this is the first study in the literature to propose and systematically evaluate probabilistic forecasts of variance in cryptocurrency markets based on predictions derived from multiple base models. Our empirical results for Bitcoin demonstrate that the Quantile Estimation through Residual Simulation (QRS) method, particularly when applied to linear base models operating on log-transformed realized volatility data, consistently outperforms more sophisticated alternatives. Additionally, we highlight the robustness of the probabilistic stacking framework, providing comprehensive insights into uncertainty and risk inherent in cryptocurrency volatility forecasting. This research fills a significant gap in the literature, contributing practical probabilistic forecasting methodologies tailored specifically to cryptocurrency markets. |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2508.15922 |
| By: | Arkadiusz Lipiecki; Kaja Bilinska; Nikolaos Kourentzes; Rafal Weron |
| Abstract: | We introduce the concept of Temporal Hierarchy Forecasting (THieF) in predicting day-ahead electricity prices and show that reconciling forecasts for hourly products, 2- to 12-hour blocks, and baseload contracts significantly (up to 13%) improves accuracy at all levels. These results remain consistent throughout a challenging 4-year test period (2021-2024) in the German power market and across model architectures, including linear regression, a shallow neural network, gradient boosting, and a state-of-the-art transformer. Given that (i) trading of block products is becoming more common and (ii) the computational cost of reconciliation is comparable to that of predicting hourly prices alone, we recommend using it in daily forecasting practice. |
| Keywords: | Electricity price; Temporal Hierarchy Forecasting (THieF); Forecast reconciliation; Regression; Machine learning |
| JEL: | C22 C45 C51 C53 Q41 Q47 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:ahh:wpaper:worms2506 |
| By: | Jieyu Chen; Sebastian Lerch; Melanie Schienle; Tomasz Serafin; Rafal Weron |
| Abstract: | The growing importance of intraday electricity trading in Europe calls for improved price forecasting and tailored decision-support tools. In this paper, we propose a novel generative neural network model to generate probabilistic path forecasts for intraday electricity prices and use them to construct effective trading strategies for Germany's continuous-time intraday market. Our method demonstrates competitive performance in terms of statistical evaluation metrics compared to two state-of-the-art statistical benchmark approaches. To further assess its economic value, we consider a realistic fixed-volume trading scenario and propose various strategies for placing market sell orders based on the path forecasts. Among the different trading strategies, the price paths generated by our generative model lead to higher profit gains than the benchmark methods. Our findings highlight the potential of generative machine learning tools in electricity price forecasting and underscore the importance of economic evaluation. |
| Keywords: | Intraday electricity market; Probabilistic forecast; Path forecast; Prediction bands; Energy score; Machine learning; Generative neural network; Trading recommendations |
| JEL: | C22 C32 C45 C51 C53 Q41 Q47 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:ahh:wpaper:worms2505 |
| By: | Arkadiusz Lipiecki; Kaja Bilinska; Nicolaos Kourentzes; Rafal Weron |
| Abstract: | We introduce the concept of temporal hierarchy forecasting (THieF) in predicting day-ahead electricity prices and show that reconciling forecasts for hourly products, 2- to 12-hour blocks, and baseload contracts significantly (up to 13%) improves accuracy at all levels. These results remain consistent throughout a challenging 4-year test period (2021-2024) in the German power market and across model architectures, including linear regression, a shallow neural network, gradient boosting, and a state-of-the-art transformer. Given that (i) trading of block products is becoming more common and (ii) the computational cost of reconciliation is comparable to that of predicting hourly prices alone, we recommend using it in daily forecasting practice. |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2508.11372 |
| By: | Rehim Kılıç |
| Abstract: | This paper fills an important gap in the volatility forecasting literature by comparing a broad suite of machine learning (ML) methods with both linear and nonlinear econometric models using high-frequency realized volatility (RV) data for the S&P 500. We evaluate ARFIMA, HAR, regime-switching HAR models (THAR, STHAR, MSHAR), and ML methods including Extreme Gradient Boosting, deep feed-forward neural networks, and recurrent networks (BRNN, LSTM, LSTM-A, GRU). Using rolling forecasts from 2006 onward, we find that regime-switching models—particularly THAR and STHAR—consistently outperform ML and linear models, especially when predictors are limited. These models also deliver more accurate risk forecasts and higher realized utility. While ML models capture some nonlinear patterns, they offer no consistent advantage over simpler, interpretable alternatives. Our findings highlight the importance of modeling regime changes through transparent econometric tools, especially in real-world applications where predictor availability is sparse and model interpretability is critical for risk management and portfolio allocation. |
| Keywords: | Realized volatility; Machine learning; Regime-switching; Nonlinearity; VaR; forecasting |
| JEL: | C10 C50 G11 G15 |
| Date: | 2025–08–08 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fedgfe:2025-61 |
| By: | Jinbo Cai; Wenze Li; Wenjie Wang |
| Abstract: | With stakeholder-level in-market data, we conduct a comparative analysis of machine learning (ML) for forecasting electricity prices in Singapore, spanning 15 individual models and 4 ensemble approaches. Our empirical findings justify the three virtues of ML models: (1) the virtue of capturing non-linearity, (2) the complexity (Kelly et al., 2024) and (3) the l2-norm and bagging techniques in a weak factor environment (Shen and Xiu, 2024). Simulation also supports the first virtue. Penalizing prediction correlation improves ensemble performance when individual models are highly correlated. The predictability can be translated into sizable economic gains under the mean-variance framework. We also reveal significant patterns of time-series heterogeneous predictability across macro regimes: predictability is clustered in expansion, volatile market and extreme geopolitical risk periods. Our feature importance results agree with the complex dynamics of Singapore's electricity market after de regulation, yet highlight its relatively supply-driven nature with the continued presence of strong regulatory influences. |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2507.07477 |
| By: | Alena Chan; Maria Garmonina |
| Abstract: | We evaluate the performance of several optimizers on the task of forecasting S&P 500 Index returns with the MambaStock model. Among the most widely used algorithms, gradient-smoothing and adaptive-rate optimizers (for example, Adam and RMSProp) yield the lowest test errors. In contrast, the Lion optimizer offers notably faster training. To combine these advantages, we introduce a novel family of optimizers, Roaree, that dampens the oscillatory loss behavior often seen with Lion while preserving its training speed. |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2508.04707 |
| By: | Yuqi Luan |
| Abstract: | This study proposes a behaviorally-informed multi-factor stock selection framework that integrates short-cycle technical alpha signals with deep learning. We design a dual-task multilayer perceptron (MLP) that jointly predicts five-day future returns and directional price movements, thereby capturing nonlinear market behaviors such as volume-price divergence, momentum-driven herding, and bottom reversals. The model is trained on 40 carefully constructed factors derived from price-volume patterns and behavioral finance insights. Empirical evaluation demonstrates that the dual-task MLP achieves superior and stable performance across both predictive accuracy and economic relevance, as measured by information coefficient (IC), information ratio (IR), and portfolio backtesting results. Comparative experiments further show that deep learning methods outperform linear baselines by effectively capturing structural interactions between factors. This work highlights the potential of structure-aware deep learning in enhancing multi-factor modeling and provides a practical framework for short-horizon quantitative investment strategies. |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2508.14656 |
| By: | Roshan Shah |
| Abstract: | We introduce a modular framework that extends the signature method to handle American option pricing under evolving volatility roughness. Building on the signature-pricing framework of Bayer et al. (2025), we add three practical innovations. First, we train a gradient-boosted ensemble to estimate the time-varying Hurst parameter H(t) from rolling windows of recent volatility data. Second, we feed these forecasts into a regime switch that chooses either a rough Bergomi or a calibrated Heston simulator, depending on the predicted roughness. Third, we accelerate signature-kernel evaluations with Random Fourier Features (RFF), cutting computational cost while preserving accuracy. Empirical tests on S&P 500 equity-index options reveal that the assumption of persistent roughness is frequently violated, particularly during stable market regimes when H(t) approaches or exceeds 0.5. The proposed hybrid framework provides a flexible structure that adapts to changing volatility roughness, improving performance over fixed-roughness baselines and reducing duality gaps in some regimes. By integrating a dynamic Hurst parameter estimation pipeline with efficient kernel approximations, we propose to enable tractable, real-time pricing of American options in dynamic volatility environments. |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2508.07151 |
| By: | Fay\c{c}al Djebari; Kahina Mehidi; Khelifa Mazouz; Philipp Otto |
| Abstract: | This paper examines several network-based volatility models for oil prices, capturing spillovers among OPEC oil-exporting countries by embedding novel network structures into ARCH-type models. We apply a network-based log-ARCH framework that incorporates weight matrices derived from time-series clustering and model-implied distances into the conditional variance equation. These weight matrices are constructed from return data and standard multivariate GARCH model outputs (CCC, DCC, and GO-GARCH), enabling a comparative analysis of volatility transmission across specifications. Through a rolling-window forecast evaluation, the network-based models demonstrate competitive forecasting performance relative to traditional specifications and uncover intricate spillover effects. These results provide a deeper understanding of the interconnectedness within the OPEC network, with important implications for financial risk assessment, market integration, and coordinated policy among oil-producing economies. |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2507.15046 |
| By: | Zhangying Li (Economics and Management School, Wuhan University); O-Chia Chuang (School of Digital Economics, Hubei University of Economics); Rangan Gupta (Department of Economics, University of Pretoria); Elie Bouri (School of Business, Lebanese American University, Lebanon) |
| Abstract: | Accurately predicting the Value-at-Risk (VaR) in commodity markets is crucial for risk management, yet the volatility and cyclicality of commodity prices pose significant challenges. This paper innovatively incorporates the information content of the Global Supply Chain Pressure Index (GSCPI) and the Global Economic Conditions Index (GECON) into the quantile Genaralized Autoregressive Conditional Heteroskedasticty-Mixed Data Sampling (GARCH-MIDAS) framework to address the issue of mismatched data frequencies, and explores the impact of these monthly indicators on daily commodity returns volatility. We find that the MIDAS framework significantly outperforms the conditional autoregressive VaR by regression quantiles (CAViaR) model, with asymmetric models showing superior performance. Both GSCPI and GECON exhibit strong explanatory power for VaR forecasting, highlighting the important influence of global supply and demand conditions on returns volatility of the overall commodity market, as well as its various sub-sectors. |
| Keywords: | VaR predictions, Quantiles-based mixed-frequency models, Commodity market |
| JEL: | C32 C53 E23 E32 Q02 |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:pre:wpaper:202528 |
| By: | Diego Vallarino |
| Abstract: | This study develops and empirically validates a Mixture of Experts (MoE) framework for stock price prediction across heterogeneous volatility regimes using real market data. The proposed model combines a Recurrent Neural Network (RNN) optimized for high-volatility stocks with a linear regression model tailored to stable equities. A volatility-aware gating mechanism dynamically weights the contributions of each expert based on asset classification. Using a dataset of 30 publicly traded U.S. stocks spanning diverse sectors, the MoE approach consistently outperforms both standalone models. Specifically, it achieves up to 33% improvement in MSE for volatile assets and 28% for stable assets relative to their respective baselines. Stratified evaluation across volatility classes demonstrates the model's ability to adapt complexity to underlying market dynamics. These results confirm that no single model suffices across market regimes and highlight the advantage of adaptive architectures in financial prediction. Future work should explore real-time gate learning, dynamic volatility segmentation, and applications to portfolio optimization. |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2508.02686 |
| By: | Jialing Han; Yu-Ning Li |
| Abstract: | We propose a novel framework for approximate factor models that integrates an S-vine copula structure to capture complex dependencies among common factors. Our estimation procedure proceeds in two steps: first, we apply principal component analysis (PCA) to extract the factors; second, we employ maximum likelihood estimation that combines kernel density estimation for the margins with an S-vine copula to model the dependence structure. Jointly fitting the S-vine copula with the margins yields an oblique factor rotation without resorting to ad hoc restrictions or traditional projection pursuit methods. Our theoretical contributions include establishing the consistency of the rotation and copula parameter estimators, developing asymptotic theory for the factor-projected empirical process under dependent data, and proving the uniform consistency of the projected entropy estimators. Simulation studies demonstrate convergence with respect to both the dimensionality and the sample size. We further assess model performance through Value-at-Risk (VaR) estimation via Monte Carlo methods and apply our methodology to the daily returns of S&P 500 Index constituents to forecast the VaR of S&P 500 index. |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2508.11619 |
| By: | Mehmet Balcilar (Department of Economics and Business Analytics, University of New Haven, West Haven, Connecticut, United States; Department of Economics, OSTIM Technical University, Ankara, Turkiye); Kenny Kutu (Department of Business Management, University of Pretoria, Pretoria, 0002, South Africa); Sonali Das (Department of Business Management, University of Pretoria, Pretoria, 0002, South Africa); Rangan Gupta (Department of Business Management, University of Pretoria, Pretoria, 0002, South Africa) |
| Abstract: | This paper analyzes the predictive effect of climate risks on inflation and inflation uncertainty in an inflation targeting emerging economy through a multivariate nonparametric higher-order causality-in-quantiles test. In this regard, we obtain a monthly Google Trends search-based Climate Attention Index for South Africa (CAI-SA), which incorporates both local and global terms dealing with physical and transition risks between January 2004 and September 2024. Using the CAI-SA, we find that linear Granger causality tests fail to show any evidence of prediction of overall and food and non-alcoholic beverages inflation rates, due to model misspecifications from nonlinearity and structural breaks. However, the robust multivariate nonparametric framework depicts statistically significant predictability over the entire conditional distribution of not only the two inflation rates, but also their respective volatilities, i.e., squared values. The strongest predictive impact is observed at the tails of the conditional distributions of the first- and second-moment of the two inflation rates. Our findings, in general, are robust to alternative definitions of inflation volatility, exclusion of the control variables, different methods of construction of the CAI, and a bootstrapped version of the test to account for size distortion and low power. Analyses involving signs of the causal impact reveal significant positive association between the CAI-SA and the inflation rates and their volatilities, thus having serious implications for monetary policy decisions in South Africa in the wake of heightened climate risks. |
| Keywords: | Climate Attention Index, Inflation, Inflation Uncertainty, Higher-Order Multivariate Causality-in-Quantiles Test, South Africa |
| JEL: | C22 C53 E31 Q54 |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:pre:wpaper:202529 |
| By: | Chenghao Liu; Aniket Mahanti; Ranesh Naha; Guanghao Wang; Erwann Sbai |
| Abstract: | As cryptocurrencies gain popularity, the digital asset marketplace becomes increasingly significant. Understanding social media signals offers valuable insights into investor sentiment and market dynamics. Prior research has predominantly focused on text-based platforms such as Twitter. However, video content remains underexplored, despite potentially containing richer emotional and contextual sentiment that is not fully captured by text alone. In this study, we present a multimodal analysis comparing TikTok and Twitter sentiment, using large language models to extract insights from both video and text data. We investigate the dynamic dependencies and spillover effects between social media sentiment and cryptocurrency market indicators. Our results reveal that TikTok's video-based sentiment significantly influences speculative assets and short-term market trends, while Twitter's text-based sentiment aligns more closely with long-term dynamics. Notably, the integration of cross-platform sentiment signals improves forecasting accuracy by up to 20%. |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2508.15825 |
| By: | Danilo Leiva-León; Viacheslav Sheremirov; Jenny Tang; Egon Zakrajšek |
| Abstract: | This paper develops an econometric framework for identifying latent factors that provide real time estimates of supply and demand conditions shaping goods- and services-related price pressures in the U.S. economy. The factors are estimated using category-specific personal consumption expenditures (PCE) data on prices and quantities, using a sign-restricted dynamic factor model that imposes theoretical predictions of the effects of fluctuations in supply and demand on prices and associated quantities through factor loadings. The resulting estimates are used to decompose total PCE inflation into contributions from common factors—goods demand, goods supply, services demand, services supply, and inflation expectations—and category specific idiosyncratic components. Validation exercises demonstrate that the estimated factors provide an informative and coherent narrative of inflation dynamics over time and can be effectively used for forecasting and policy analysis. |
| Keywords: | inflation; goods; services; supply; demand; expectations; dynamic factor models; sign restrictions; factor loadings |
| JEL: | C11 C32 E31 |
| Date: | 2025–08–01 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fedbwp:101428 |
| By: | Paul Glasserman; Kriste Krstovski; Paul Laliberte; Harry Mamaysky |
| Abstract: | Over the past 30 years, nearly all the gains in the U.S. stock market have been earned overnight, while average intraday returns have been negative or flat. We find that a large part of this effect can be explained through features of intraday and overnight news. Our analysis uses a collection of 2.4 million news articles. We apply a novel technique for supervised topic analysis that selects news topics based on their ability to explain contemporaneous market returns. We find that time variation in the prevalence of news topics and differences in the responses to news topics both contribute to the difference in intraday and overnight returns. In out-of-sample tests, our approach forecasts which stocks will do particularly well overnight and particularly poorly intraday. Our approach also helps explain patterns of continuation and reversal in intraday and overnight returns. We contrast the effect of news with other mechanisms proposed in the literature to explain overnight returns. |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2507.04481 |
| By: | Ece Fisgin; Joaquin Garcia-Cabo; Alex Haag; Mitch Lott |
| Abstract: | We present a principal component analysis of euro area labor market conditions by combining information from 22 labor market indicators into two comprehensive series. These two novel indicators provide a systematic view of the current state and forward-looking direction of the euro-area labor market, respectively, and demonstrate superior forecasting performance compared to existing indicators. Crucially, we find significant implications for monetary policy design: a local projection analysis reveals that ECB monetary policy shocks have attenuated effects on both inflation and unemployment when the labor market forward-looking indicator is high. The dampened inflation response calls for tighter policy rate paths than a standard Taylor rule would prescribe. Finally, we show that focusing solely on the official unemployment rate may understate the actual labor market slack, and consequently, the trade-off between labor market health and inflationary dynamics. |
| Keywords: | Employment; Unemployment; Labor market forecasting; European labor market |
| JEL: | E24 E27 J63 |
| Date: | 2025–08–13 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fedgif:1415 |
| By: | Little, Andrew T.; Moore, Don A (University of California, Berkeley); Augenblick, Ned; Backus, Matthew |
| Abstract: | Constructing beliefs about the world often requires simplifying assumptions. However, it is often cognitively costly or even impossible to consider how all possible assumptions might affect beliefs. We develop a formal model of individuals who properly recognize uncertainty conditional on their assumptions (“within-model uncertainty”), but do not fully appreciate the uncertainty they assume away (“across-model uncertainty”). Our main results connect this tendency to use simplified models with overprecision (too-small variance estimates) and disagreement (interpersonal variance in mean predictions). If individuals independently choose an assumption in proportion to its probability of being true, across-model uncertainty, overprecision, and disagreement exactly coincide. We explore these predictions in an experimental setting where people are given a scatterplot and provide mean and ariance estimates for out-of-sample predictions. Consistent with the theory, we find that variance stimates are more responsive to changes in within-model uncertainty than across-model uncertainty, nd that overprecision and disagreement rise with across-model uncertainty. Finally, we analyze observational data from the Survey of Professional Forecasters, and find that forecasts are overprecise, and more overprecise in problems with more disagreement. |
| Date: | 2025–08–22 |
| URL: | https://d.repec.org/n?u=RePEc:osf:osfxxx:mnv4k_v1 |