Journal of Forecasting最新文献

Accurate wind speed prediction is of great importance for the operation of wind farms, and extensive efforts have been made to develop effective forecasting methods in this regard. However, the feature selection of data input as well as optimization of deep learning models have received comparatively less attention, leading to unreliable forecasting results. This research proposes a novel hybrid model that integrates data preprocessing, feature selection, and optimized forecasting for improved wind speed prediction. Specifically, a powerful preprocessing technique is utilized to reduce data noise disturbances, while an innovative two-stage feature selection is designed to achieve the optimal input data format for forecasting purposes. Moreover, a hybrid forecasting module based on long-short term memory, which is optimized by the Bayesian optimization algorithm, has been developed to enhance the efficiency and reliability of the model. The empirical study used 10-min interval wind speed data of four seasons for presentation and evaluation results demonstrated its superior performance in effectively learning the volatility and irregularity features of wind speed series, which established a solid foundation for practical applications in wind power systems.

In a collaborative supply chain arrangement like vendor-managed inventory, information on product demand at the point of sale is expected to be shared among members of the supply chain. However, in practice, obtaining such information can be costly, and some members may be unwilling or unable to provide the necessary access to the data. As such, large collaborative supply chains with multiple members may operate under a mixed-information scenario where point-of-sale demand information is not known for all customers. Other sources of demand information exist and are becoming more available along supply chains using Industry 4.0 technologies and can serve as a substitute, but the data may be noisy, distorted, and partially missing. Under mixed information, leveraging existing customers' point-of-sale demand to improve the intermittent demand forecast of customers with missing information has yet to be explored. We propose a supervised demand forecasting method that uses multivariate time series clustering to map multiple sources of demand data. Members with missing downstream demand data have their resulting demand forecast improved by averaging over customers with similar delivery patterns for their final demand forecast. Our results show up to a 10% accuracy improvement over traditional intermittent demand forecasting methods with missing information.

In this paper, the self-monitoring learning model FinBERT is used to identify text emotions, and the sliding time window time-lagged cross-correlation (WTLCC) method is utilized to screen Baidu Index keywords for the Shanghai Stock Exchange Index and 18 A-share listed companies. There are five different types of indicators constructed: news media sentiment, public attention, investor sentiment, investor sentiment disagreement, and media sentiment disagreement. To accurately describe the structure of sentimental contagion, this paper combines graph neural network to learn and output the sentimental contagion graph, and then constructs multivariable time series forecasting with graph neural networks (MTGNN) volatility forecasting model, which can extract the spatial–temporal dependence of variables in pairs. The results show that MTGNN model possesses the highest forecasting accuracy, which performs 30.30% lower on average across four evaluation indicators for Shanghai Stock Exchange Index than temporal pattern attention–long short-term memory model, which ranks second. For all of the models considered in this paper, adding sentimental contagion mechanism can significantly improve the volatility forecasting accuracy. The error of MTGNN is reduced the most, with a 15.21% average reduction for the Shanghai Stock Exchange Index. The contagion relationship among media reports, investor sentiment, and attention can help provide new ideas for enhancing the precision of volatility forecasting from the public opinion environment in the financial market.

In recent years, ensuring food security has become a global concern, necessitating accurate forecasting of agriculture security to aid in policymaking and resource allocation. This article proposes the utilization of transformers, a powerful deep learning technique, for predicting the Agriculture Security Index ($�A�S�I$). The $�A�S�I$ is a comprehensive metric that evaluates the stability and resilience of agricultural systems. By harnessing the temporal dependencies and complex patterns present in historical $�A�S�I$ data, transformers offer a promising approach for accurate and reliable forecasting. The transformer architecture, renowned for its ability to capture long-range dependencies, is tailored to suit the $�A�S�I$ forecasting task. The model is trained using a combination of supervised learning and attention mechanisms to identify salient features and capture intricate relationships within the data. To evaluate the performance of the proposed method, various evaluation metrics, including mean absolute error, root mean square error, and coefficient of determination, are employed to assess the accuracy, robustness, and generalizability of the transformer-based forecasting approach. The results obtained demonstrate the efficacy of transformers in forecasting the $�A�S�I$, outperforming traditional time series forecasting methods. The transformer model showcases its ability to capture both short-term fluctuations and long-term trends in the $�A�S�I$, allowing policymakers and stakeholders to make informed decisions. Additionally, the study identifies key factors that significantly influence agriculture security, providing valuable insights for proactive intervention and resource allocation.

We implement a novel nonlinear structural model featuring an empirically successful frequency-dependent and asymmetric Phillips curve; unemployment frequency components interact with three components of core personal consumption expenditures (PCE)—core goods, housing, and core services ex-housing—and a variable capturing supply shocks. Forecast tests verify accuracy in its unemployment–inflation trade-offs, crucial for monetary policy. Using this model, we assess the plausibility of the December 2022 Summary of Economic Projections (SEP). By 2025Q4, the SEP projects 2.1% inflation; however, conditional on the SEP unemployment path, we project 2.9%. A fairly deep recession delivers the SEP inflation path, but a simple welfare analysis rejects this outcome.

The predictive and interpretable power of models is crucial for financial risk management. The purpose of this study was to perform credit risk prediction in a structured causal network with four stages—data processing, structural learning, parameter learning, and interpretation of inferences—and use six real credit datasets to conduct empirical research on the proposed model. Compared with traditional machine learning algorithms, we comprehensively explain the results of credit default through forward and reverse reasoning. We also compared our model with the post hoc interpretation models local interpretable model-agnostic explanations (LIME) and shapley additive explanations (SHAP) to verify the interpretability of Bayesian networks. The experimental results show that the prediction performance of Bayesian networks is superior to traditional machine learning models and similar to the performance of ensemble models. Furthermore, Bayesian networks offer valuable insights into the interplay of features by considering their causal relationships and enable an assessment of how individual features influence the prediction outcome. In this study, what-if analysis was performed to assess credit default probabilities under various conditions. This analysis provides decision-makers with the necessary tools to make informed judgments about the risk profile of borrowers. Consequently, we consider Bayesian networks as a viable tool for credit risk prediction models in terms of prediction performance and interpretability.

This paper examines the predictability of the changes in Brent oil futures prices using a multilayer perceptron artificial neural network that exploits the information contained in the largest possible set of economic indicators. Feature engineering is employed to identify the most important predictors of the change in Brent oil futures prices. We find that oil-market-specific variables are important predictors. Our findings also suggest that forecasts of the change in the Brent oil futures prices from the multilayer perceptron that exploits the informational content of all and oil-market-specific predictors exhibit higher statistical forecast accuracy than the random walk. Tests of forecast optimality indicate that the forecasts generated using oil-market-specific predictors are optimal. We discuss the policymaking and practical relevance of our results.

Efforts in corn future price forecasting and early warning play a vital role in guiding the high-quality development of the agricultural economy. However, recent years have witnessed significant fluctuations in global corn future prices due to the impact of COVID-19 and the escalating risks associated with geopolitical conflicts. Therefore, there is an urgent need for accurate and efficient methods to forecast corn future prices. To address this challenge, a novel and comprehensive framework for explainable corn future price forecasting is designed. This framework takes into account multiple factors contributing to corn price volatility, including supply and demand dynamics, policy adjustments, international market shocks, global geopolitical risks, and investor concerns within the corn market. During the data processing stage, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is utilized to thoroughly explore the volatility characteristics of historical corn future prices. Additionally, a convolutional neural network (CNN) is employed to extract essential forecasting information from corn news data. To enhance interpretability, a novel JADE–TFT interpretable corn future price prediction model is proposed. This model combines adaptive differential evolution with optional external archiving (JADE) to intelligently and efficiently optimize the parameters of the temporal fusion transformers (TFTs). Furthermore, in the empirical study, the introduction of a global geopolitical risk coefficient, Baidu indices such as “corn” and “corn price,” and quantized corn news text features is shown to improve the accuracy of corn future price predictions. The proposed corn future price prediction framework contributes to the healthy development of the global grain futures market, thereby fostering the growth and well-being of enterprises involved in the grain industry.

The k-nearest neighbors algorithm is one of the prominent techniques used in classification and regression. Despite its simplicity, the k-nearest neighbors has been successfully applied in time series forecasting. However, the selection of the number of neighbors and feature selection is a daunting task. In this paper, we introduce two methodologies for forecasting time series that we refer to as Classical Parameters Tuning in Weighted Nearest Neighbors and Fast Parameters Tuning in Weighted Nearest Neighbors. The first approach uses classical parameters tuning that compares the most recent subsequence with every possible subsequence from the past of the same length. The second approach reduces the neighbors' search set, which leads to significantly reduced grid size and hence a lower computational time. To tune the models' parameters, both methods implement an approach inspired by cross-validation for weighted nearest neighbors. We evaluate the forecasting performance and accuracy of our models. Then, we compare them to other approaches, especially, Seasonal Autoregressive Integrated Moving Average, Holt Winters, and Exponential Smoothing State Space Model. Real data examples on retail and food services sales in the United States and milk production in the United Kingdom are analyzed to demonstrate the application and efficiency of the proposed approaches.

This paper introduces a new indicator for reported intimate partner violence against women based on search query time series from Google Trends. This indicator is built up from the relative popularity of three topic-related keywords. We propose a predictive model based on this specific Google index that is assessed relative to two alternative models: the first one includes the lagged variable, while the second one considers fatalities as a predictor. This comparative analysis is run in two different samples, whether the reported cases are a direct consequence of a violent direct or not. Our results show that the predictive model based on Google data significantly outperforms the other two models, regardless the sample and the forecast horizon. Then, using information gathered from Google queries may improve the allocation and management of resources and services to protect women against this form of violence and to improve risk assessment.