|
on Forecasting |
| By: | Timoth\'ee Hornek Amir Sartipi; Igor Tchappi; Gilbert Fridgen |
| Abstract: | Accurate electricity price forecasting (EPF) is crucial for effective decision-making in power trading on the spot market. While recent advances in generative artificial intelligence (GenAI) and pre-trained large language models (LLMs) have inspired the development of numerous time series foundation models (TSFMs) for time series forecasting, their effectiveness in EPF remains uncertain. To address this gap, we benchmark several state-of-the-art pretrained models--Chronos-Bolt, Chronos-T5, TimesFM, Moirai, Time-MoE, and TimeGPT--against established statistical and machine learning (ML) methods for EPF. Using 2024 day-ahead auction (DAA) electricity prices from Germany, France, the Netherlands, Austria, and Belgium, we generate daily forecasts with a one-day horizon. Chronos-Bolt and Time-MoE emerge as the strongest among the TSFMs, performing on par with traditional models. However, the biseasonal MSTL model, which captures daily and weekly seasonality, stands out for its consistent performance across countries and evaluation metrics, with no TSFM statistically outperforming it. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.08113 |
| By: | Tobias Adrian; Domenico Giannone; Matteo Luciani; Mike West |
| Abstract: | We introduce methodology to bridge scenario analysis and model-based risk forecasting, leveraging their respective strengths in policy settings. Our Bayesian framework addresses the fundamental challenge of reconciling judgmental narrative approaches with statistical forecasting. Analysis evaluates explicit measures of concordance of scenarios with a reference forecasting model, delivers Bayesian predictive synthesis of the scenarios to best match that reference, and addresses scenario set incompleteness. This underlies systematic evaluation and integration of risks from different scenarios, and quantifies relative support for scenarios modulo the defined reference forecasts. The framework offers advances in forecasting in policy institutions that supports clear and rigorous communication of evolving risks. We also discuss broader questions of integrating judgmental information with statistical model-based forecasts in the face of unexpected circumstances. |
| Keywords: | Macroeconomic Forecasting; Mixtures of Scenarios; Misclassification Rates; Entropic Tilting; Bayesian Predictive Synthesis; Judgmental Forecasting; Forecast Risk Assessment |
| Date: | 2025–05–20 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fedgfe:2025-36 |
| By: | Joann Jasiak; Cheng Zhong |
| Abstract: | We study the Functional PCA (FPCA) forecasting method in application to functions of intraday returns on Bitcoin. We show that improved interval forecasts of future return functions are obtained when the conditional heteroscedasticity of return functions is taken into account. The Karhunen-Loeve (KL) dynamic factor model is introduced to bridge the functional and discrete time dynamic models. It offers a convenient framework for functional time series analysis. For intraday forecasting, we introduce a new algorithm based on the FPCA applied by rolling, which can be used for any data observed continuously 24/7. The proposed FPCA forecasting methods are applied to return functions computed from data sampled hourly and at 15-minute intervals. Next, the functional forecasts evaluated at discrete points in time are compared with the forecasts based on other methods, including machine learning and a traditional ARMA model. The proposed FPCA-based methods perform well in terms of forecast accuracy and outperform competitors in terms of directional (sign) of return forecasts at fixed points in time. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.20508 |
| By: | Sukru Selim Calik; Andac Akyuz; Zeynep Hilal Kilimci; Kerem Colak |
| Abstract: | Financial literacy is increasingly dependent on the ability to interpret complex financial data and utilize advanced forecasting tools. In this context, this study proposes a novel approach that combines transformer-based time series models with explainable artificial intelligence (XAI) to enhance the interpretability and accuracy of stock price predictions. The analysis focuses on the daily stock prices of the five highest-volume banks listed in the BIST100 index, along with XBANK and XU100 indices, covering the period from January 2015 to March 2025. Models including DLinear, LTSNet, Vanilla Transformer, and Time Series Transformer are employed, with input features enriched by technical indicators. SHAP and LIME techniques are used to provide transparency into the influence of individual features on model outputs. The results demonstrate the strong predictive capabilities of transformer models and highlight the potential of interpretable machine learning to empower individuals in making informed investment decisions and actively engaging in financial markets. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.06345 |
| By: | Xin Tian |
| Abstract: | This report presents a comprehensive evaluation of three Value-at-Risk (VaR) modeling approaches: Historical Simulation (HS), GARCH with Normal approximation (GARCH-N), and GARCH with Filtered Historical Simulation (FHS), using both in-sample and multi-day forecasting frameworks. We compute daily 5 percent VaR estimates using each method and assess their accuracy via empirical breach frequencies and visual breach indicators. Our findings reveal severe miscalibration in the HS and GARCH-N models, with empirical breach rates far exceeding theoretical levels. In contrast, the FHS method consistently aligns with theoretical expectations and exhibits desirable statistical and visual behavior. We further simulate 5-day cumulative returns under both GARCH-N and GARCH-FHS frameworks to compute multi-period VaR and Expected Shortfall. Results show that GARCH-N underestimates tail risk due to its reliance on the Gaussian assumption, whereas GARCH-FHS provides more robust and conservative tail estimates. Overall, the study demonstrates that the GARCH-FHS model offers superior performance in capturing fat-tailed risks and provides more reliable short-term risk forecasts. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.05646 |
| By: | Mihai Cucuringu; Kang Li; Chao Zhang |
| Abstract: | This study focuses on forecasting intraday trading volumes, a crucial component for portfolio implementation, especially in high-frequency (HF) trading environments. Given the current scarcity of flexible methods in this area, we employ a suite of machine learning (ML) models enriched with numerous HF predictors to enhance the predictability of intraday trading volumes. Our findings reveal that intraday stock trading volume is highly predictable, especially with ML and considering commonality. Additionally, we assess the economic benefits of accurate volume forecasting through Volume Weighted Average Price (VWAP) strategies. The results demonstrate that precise intraday forecasting offers substantial advantages, providing valuable insights for traders to optimize their strategies. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.08180 |
| By: | Juvonen, Petteri; Lindblad, Annika |
| Abstract: | We analyse the accuracy of an econometric model for nowcasting GDP growth in a true real-time setting. The analysis is based on a unique sample of nowcasts that were produced in real time and stored. Our results support the use of econometric models for nowcasting because the accuracy of these real-time nowcasts is found to be comparable to the first GDP estimates of the statistical authority. The nowcasts are produced by a large Bayesian vector autoregressive model. We find the model fares well against other statistical models, and the results suggest that its performance has been more robust to COVID-19 fluctuations than that of a dynamic factor model. We also analyse comments on the nowcast tweets published on Twitter in real time. |
| Keywords: | Nowcasting, Real-time analysis, Vector autoregressions, Bayesian methods, Mixed frequency, Business cycles |
| JEL: | C11 C52 C53 E32 E37 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:zbw:bofrdp:319609 |
| By: | Austin Pollok |
| Abstract: | The discrepancy between realized volatility and the market's view of volatility has been known to predict individual equity options at the monthly horizon. It is not clear how this predictability depends on a forecast's ability to predict firm-level volatility. We consider this phenomenon at the daily frequency using high-dimensional machine learning models, as well as low-dimensional factor models. We find that marginal improvements to standard forecast error measurements can lead to economically significant gains in portfolio performance. This makes a case for re-imagining the way we train models that are used to construct portfolios. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.07928 |
| By: | David T. Frazier; Donald S. Poskitt |
| Abstract: | This paper shows that sequential statistical analysis techniques can be generalised to the problem of selecting between alternative forecasting methods using scoring rules. A return to basic principles is necessary in order to show that ideas and concepts from sequential statistical methods can be adapted and applied to sequential scoring rule evaluation (SSRE). One key technical contribution of this paper is the development of a large deviations type result for SSRE schemes using a change of measure that parallels a traditional exponential tilting form. Further, we also show that SSRE will terminate in finite time with probability one, and that the moments of the SSRE stopping time exist. A second key contribution is to show that the exponential tilting form underlying our large deviations result allows us to cast SSRE within the framework of generalised e-values. Relying on this formulation, we devise sequential testing approaches that are both powerful and maintain control on error probabilities underlying the analysis. Through several simulated examples, we demonstrate that our e-values based SSRE approach delivers reliable results that are more powerful than more commonly applied testing methods precisely in the situations where these commonly applied methods can be expected to fail. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.09090 |
| By: | Lukas Bauer; Ekaterina Kazak |
| Abstract: | This paper proposes a Conditional Method Confidence Set (CMCS) which allows to select the best subset of forecasting methods with equal predictive ability conditional on a specific economic regime. The test resembles the Model Confidence Set by Hansen et al. (2011) and is adapted for conditional forecast evaluation. We show the asymptotic validity of the proposed test and illustrate its properties in a simulation study. The proposed testing procedure is particularly suitable for stress-testing of financial risk models required by the regulators. We showcase the empirical relevance of the CMCS using the stress-testing scenario of Expected Shortfall. The empirical evidence suggests that the proposed CMCS procedure can be used as a robust tool for forecast evaluation of market risk models for different economic regimes. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.21278 |
| By: | Sofia Velasco |
| Abstract: | This article proposes a novel framework that integrates Bayesian Additive Regression Trees (BART) into a Factor-Augmented Vector Autoregressive (FAVAR) model to forecast macro-financial variables and examine asymmetries in the transmission of oil price shocks. By employing nonparametric techniques for dimension reduction, the model captures complex, nonlinear relationships between observables and latent factors that are often missed by linear approaches. A simulation experiment comparing FABART to linear alternatives and a Monte Carlo experiment demonstrate that the framework accurately recovers the relationship between latent factors and observables in the presence of nonlinearities, while remaining consistent under linear data-generating processes. The empirical application shows that FABART substantially improves forecast accuracy for industrial production relative to linear benchmarks, particularly during periods of heightened volatility and economic stress. In addition, the model reveals pronounced sign asymmetries in the transmission of oil supply news shocks to the U.S. economy, with positive shocks generating stronger and more persistent contractions in real activity and inflation than the expansions triggered by negative shocks. A similar pattern emerges at the U.S. federal state level, where negative shocks lead to modest declines in employment compared to the substantially larger contractions observed after positive shocks. |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2506.11551 |
| By: | Bernardina Algieri; Leonardo Iania; Arturo Leccadito; Giulia Meloni |
| Abstract: | Can we predict fine wine and alcohol prices? Yes, but it depends on the forecasting horizon. We make this point by considering the Liv-ex Fine Wine 100 and 50 Indices, the retail and wholesale alcohol prices in the United States for the period going from January 1992 to March 2022. We use rich and diverse datasets of economic, survey, and financial variables as potential price drivers and adopt several combination/dimension reduction techniques to extract the most relevant determinants. We build a comprehensive set of models and compare forecast performances across different selling levels and alcohol categories. We show that it is possible to predict fine wine prices for the 2-year horizon and retail/wholesale alcohol prices at horizons ranging from 1 month to 2 years. Our findings stress the importance of including consumer survey data and macroeconomic factors, such as international economic factors and developed markets equity risk factors, to enhance the precision of predictions of retail/wholesale (fine wine) prices. |
| Keywords: | alcohol retail and wholesale prices; dimensionality reduction; forecasting models; Liv-ex Fine Wine Indices |
| Date: | 2024–02 |
| URL: | https://d.repec.org/n?u=RePEc:ulb:ulbeco:2013/374676 |
| By: | Wenhao Guo; Yuda Wang; Zeqiao Huang; Changjiang Zhang; Shumin ma |
| Abstract: | In the complex landscape of traditional futures trading, where vast data and variables like real-time Limit Order Books (LOB) complicate price predictions, we introduce the FutureQuant Transformer model, leveraging attention mechanisms to navigate these challenges. Unlike conventional models focused on point predictions, the FutureQuant model excels in forecasting the range and volatility of future prices, thus offering richer insights for trading strategies. Its ability to parse and learn from intricate market patterns allows for enhanced decision-making, significantly improving risk management and achieving a notable average gain of 0.1193% per 30-minute trade over state-of-the-art models with a simple algorithm using factors such as RSI, ATR, and Bollinger Bands. This innovation marks a substantial leap forward in predictive analytics within the volatile domain of futures trading. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.05595 |
| By: | Liexin Cheng; Xue Cheng; Shuaiqiang Liu |
| Abstract: | This paper demonstrates that a broad class of problems in quantitative finance, including those previously addressed using deep neural networks, can be efficiently solved using single-layer neural networks without iterative gradient-based training, namely extreme learning machine (ELM). ELM utilizes a single-layer network with randomly initialized hidden nodes and analytically computed output weights obtained via convex optimization, enabling rapid training and inference. Both supervised and unsupervised learning tasks are explored. In supervised learning, ELM is employed to learn parametric option pricing functions, predict intraday stock returns, and complete implied volatility surfaces. Compared with deep neural networks, Gaussian process regression, and logistic regression, ELM achieves higher computational speed, comparable accuracy, and superior generalization. In unsupervised learning, ELM numerically solves Black-Scholes-type PDEs, and outperforms Physics-Informed Neural Networks in training speed without losing precision. The approximation and generalization abilities of ELM are briefly discussed. The findings establish ELM as a practical and efficient tool for various tasks in quantitative finance. |
| Date: | 2025–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2505.09551 |
| By: | Ulrike Famira-Mühlberger (WIFO); Klaus Nowotny |
| Abstract: | We use administrative microdata and statistical learning methods to analyse how personal characteristics and the consumption of healthcare services help predict the first-time receipt of "long-term care allowance" (LTCA), a needs-tested cash-for-care benefit in Austria. Our findings suggest that short-term information from the health-care sector, particularly in the quarter prior to LTCA enrolment, provides substantial explanatory power. Apart from old age, the most influential predictors include the frequency of doctor visits and hospital stays as well as diagnoses such as dementia, cerebral infarction, and hypertension. Our findings emphasise the importance of data-driven approaches in anticipating the uptake of long-term care benefits and informing policy, especially against the background of the demographic transition. |
| Date: | 2025–06–18 |
| URL: | https://d.repec.org/n?u=RePEc:wfo:wpaper:y:2025:i:707 |
| By: | Vecgaile, Linda; Spata, Alessandro; Vecchietti, Luiz Felipe; Zagheni, Emilio |
| Abstract: | Life course sequences are complex trajectories of interconnected events that shape the future of individuals in multifaceted ways. Life course research often predicts single life events at specific stages, overlooking the sequential and dynamic nature of human lives. Additionally, the inherent uncertainty in life leads to various potential alternative pathways individuals may encounter. In this study, we perform sequence analysis to gain deeper insights into life course sequences and apply Transformers to model sequences of future life events focusing on individuals in Germany who are approaching retirement age. Our model forecasts these sequences from which we provide probabilistic assessments of alternative pathways. Through our analysis, we identify seven distinct late-career clusters, ranging from stable full-time employment, which exhibit high predictability and certainty, to persistent unemployment and marginal employment, which demonstrate greater volatility and uncertainty. Alternative pathways predicted by the model suggest that individuals in volatile career trajectories might have transitioned into stable employment under different opportunity structures. These findings underscore the potential for stability based on prior life course patterns and highlight the importance of proactive labor market policies. Our framework provides policymakers with actionable insights to design effective interventions aimed at supporting vulnerable populations and enhancing labor market policies. |
| Date: | 2025–06–11 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:7ut9m_v1 |