Journal of Forecasting最新文献

There are 21,999 China utility model patents with existing decisions of invalidation reexamination from 2000 to 2021 to explore application of support vector machine (SVM) with Gaussian radial basis function (RBF) kernel. This study identified significant patent indicators using analysis of variance (ANOVA), Kruskal–Wallis test, and Jonckheere–Terpstra ordered-alternatives test and employed SVM incorporating significant patent indicators to forecast decision of invalidation reexamination with highest accuracy for patents with fully invalid claims. The study confirmed SVM with RBF to forecast patent sustainability and providing support for due diligence in mergers and acquisitions and litigation strategies.

This study adopts a component-driven approach to improve FX volatility and value-at-risk (VaR) forecasts, with a focus on two types of leading indicators: currency indexes and sovereign spreads. Specifically, we explore the significance of the US dollar index, RMB index, and China–US 10-year sovereign bond yield spread, as long-term volatility components in GARCH-MIDAS models for the USDCNH exchange rate. The investigation reveals that these explanatory variables have a substantial influence on the market's volatility. In terms of the enhanced prediction of volatility and VaR, our analysis presents empirical evidence for the forecasting superiority of the GARCH-MIDAS models that fully exploit the aforementioned variables and their combinations. Improving upon the traditional method, the optimal GARCH-MIDAS specification is comparable to or even outperforms the intraday high-frequency realized volatility model. Our research contributes to a deeper understanding of the influential factors behind USDCNH fluctuations and advances an effective method to accurately forecast volatility and VaR from component-driven perspectives.

Accurate precipitation prediction is vital for effective water resource management, agricultural planning, and natural disaster mitigation. Traditional forecasting methods often encounter difficulties due to the nonlinearity, complex seasonality, and noise inherent in meteorological data. This paper introduces a novel methodology that combines the FB–Prophet algorithm, designed by Facebook for identifying trends and seasonal patterns, with a fuzzy clustering algorithm. This integration aims to refine a crucial aspect of the FB–Prophet framework: the identification and incorporation of special events, specifically holidays, which play a significant role in the predictive modeling process. This approach ensures that holidays are effectively integrated into forecasts, enhancing the model's overall accuracy and reliability. Additionally, the proposed model is compared to several widely used algorithms in recent studies in terms of accuracy, employing nonparametric tests for a robust evaluation. Empirical results demonstrate a significant improvement in forecast accuracy over traditional methods.

This study examines the predictive performance of Feature Attention (FA), Temporal Attention (TA), and Feature and Temporal Attention (FATA) within Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and Transformer architectures using price data from four Chinese carbon markets (CEA, BEA, GDEA, and HBEA). Drawing on multiple forecasting accuracy measures and significance testing, the results show that attention mechanisms can enhance forecasting accuracy in certain market-model combinations, but their effectiveness critically depends on the alignment among market conditions, model architectures, and attention mechanisms. In markets with high average prices and volatility, FA achieves the best performance with GRU and LSTM; in lower price, moderately volatile markets, TA combined with Transformer is more effective; and in the high-price, high-volatility CEA market, FATA shows promise when paired with Transformer, but lacks robustness across markets. These findings highlight a pronounced compatibility pattern among market conditions, model architectures, and attention mechanisms, suggesting that the deployment of attention mechanisms in carbon price forecasting should be tailored to specific market conditions and model structures rather than applied universally.

Accurate volatility prediction is essential for guiding investor decision-making, assessing financial stability, and managing risk. The efficacy of volatility prediction is an important issue that hinges on selecting relevant factors and applying robust analytical tools. Therefore, we propose a novel decomposition-learning method that integrates deep-learning techniques for volatility prediction. Specifically, the study employs convolutional neural networks (CNN) and long short-term memory (LSTM) networks to capture the nonlinear features in time series data. To enhance the model's predictive capabilities, we introduce singular spectrum analysis (SSA) and develop a feature contribution evaluation algorithm to identify and filter out the factors exerting the greatest influence. Building on this foundation, we construct the SSA-CNN-LSTM model that supports dual volatility prediction and evaluates each feature's contribution. We design and implement the framework and algorithms for this new approach, applying it to volatility prediction for major global stock indices. The results show that: (1) the trend, cycle, and perturbation components extracted from realized volatility outperform external factors in prediction; and (2) eliminating the features with the lowest contribution significantly enhances the model's predictive performance, thus providing financial markets with a more accurate volatility prediction tool.

Considering that, in the recent past, several studies have reasserted that human judgment is still valuable for forecasting in supply chains, this paper proposes a demand forecasting decision model (DFDM), which mathematically integrates expert judgment estimates with forecasts generated from time series and machine-learning models. An interval 3-point elicitation procedure has been used to effectively obtain estimates from experts, and further, a mathematical bias adjustment mechanism is used to detect and eliminate any systematic bias in experts' forecasts. The real-life data from manufacturing and retail firms are collected to test the proposed model. The independent variables in the data are taken as interval data series rather than crisp values to capture the uncertainty in the variables and use them for forecasting models. Error metrics to measure bias (mean error), accuracy (mean absolute error), and variance (mean squared error) of forecasts were used to evaluate the performance of the proposed DFDM. The forecasts from the proposed model were found to be significantly better than those from popular forecasting methods in practice. Finally, using temporal disaggregation, an extension to the proposed models is presented to generate very short-term forecasts to help managers make better short-term operational decisions.

Our expectation of stock price trends is the main factor in making a trading strategy or determining the right time to buy or sell a stock. Predictions on stock market prices are a great challenge due to its complexity and the dependence of prices on various economic and non-economic factors. Today, technological advances have led to proposing new methods in this field. Deep learning is one of these methods that has received much attention in recent years. In this study, using deep learning methods and, more specifically, long-short term memory (LSTM) and gated recurrent unit (GRU) networks, we predict the S&P 500 index in three different time frames: daily, weekly, and monthly. We also compare the efficiency of these two methods and examine the effect of choosing different time frames for the input data of these networks. The results indicate that the GRU network outperforms the LSTM network. Also, selecting an appropriate time frame for the input data may improve the network accuracy.

In response to the research demand for forecasting European Union Allowance (EUA) prices, this paper proposes a probabilistic forecasting framework based on a spatiotemporal convolutional neural network. This framework innovatively integrates multidimensional external uncertainty indicators, captures the long-term dependencies of carbon prices through a spatiotemporal convolutional structure, and combines quantile regression with conformal prediction to effectively estimate prediction intervals. Empirical studies demonstrate that the proposed TCN-iTransformer model outperforms existing methods in both point prediction and interval prediction, exhibiting excellent prediction interval coverage probability and normalized average width at different confidence intervals. The Diebold–Mariano (DM) test and ordinary least squares (OLS) regression analysis further validate the predictive advantages of the proposed model. Furthermore, SHAP analysis reveals that the U.S. Treasury yield spread has the most significant impact on EUA price forecasting, while geopolitical risks predominantly exert negative effects. The research findings provide important references for constructing risk mitigation strategies in the European Union carbon emissions market under complex market environments.

We examine the time-varying jump behavior of the Chinese stock market across various time scales. A novel hybrid model (VMD-ARJI-X) is proposed that integrates variational mode decomposition (VMD) with the autoregressive jump intensity model (ARJI), which also incorporates monetary policy and investor sentiment as explicit variables. Results indicate that the interactions between monetary policy and investor sentiment significantly amplify jump risk at the short- and medium-term scales, while the effect is less pronounced over long-term horizons. The predictive capability of the VMD-ARJI-X, which embeds interest rate and investor sentiment into the jump intensity component, outperforms other benchmark models. Our findings provide policymakers with actionable insights for identifying extreme risks triggered by both policy and sentiment and obtaining forward-looking warnings. The multiscale jump signals offer a practical tool to design dynamic risk management strategies for investors.

Accurate prediction of carbon prices is crucial for policymakers, investors, and other participants in emissions trading schemes (ETS) and during regulatory transitions. In this work, carbon price movements are forecasted using a nonlinear ARIMA model as the baseline, alongside XGBoost and LSTM as competing models. The widely adopted XGBoost model is a machine learning (ML) technique, while the LSTM model belongs to the class of Recurrent Neural Network (RNN) models. To harness the predictive strengths of both approaches, we also employ a hybrid model that averages forecasts from the LSTM and XGBoost models. The dataset used in this study is in daily format, ranging from December 1, 2010, to January 10, 2025. The results show that both XGBoost and LSTM outperform the baseline ARIMA model. Furthermore, the hybrid model demonstrates statistically significant improvements in forecasting accuracy compared to the baseline model. These findings suggest that ML- and RNN-based approaches can serve as effective alternatives to traditional statistical and econometric models in carbon pricing forecasting.