Journal of Forecasting最新文献

{"title":"Data-Driven Predictive Modeling of Citywide Crowd Flow for Urban Safety Management: A Case Study of Beijing, China","authors":"He Jiang, Xuxilu Zhang, Yao Dong, Jianzhou Wang","doi":"10.1002/for.3216","DOIUrl":"https://doi.org/10.1002/for.3216","url":null,"abstract":"<div>\u0000 \u0000 <p>Crowd flow forecasting is vital for urban planning, resource allocation, and public safety, particularly in the context of the COVID-19 pandemic. However, traditional predictive models struggle to capture the complex, nonlinear spatial–temporal relationships inherent in crowd flow data due to its irregular volatility. To address these limitations, this paper proposes the innovative citywide crowd flow prediction (CCFP) model, which merges statistical rules with machine learning techniques (XGBoost, LightGBM, and CatBoost). The CCFP model is specifically designed to leverage spatial dependencies and two-level periodicity (weekly and daily) in population flow to predict crowd flow indexes (\u0000<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>C</mi>\u0000 <mi>F</mi>\u0000 <mi>I</mi>\u0000 </mrow>\u0000 <annotation>$$ CFI $$</annotation>\u0000 </semantics></math>) within specific areas. We employ an urban area graph created using the Node2Vec algorithm to capture the temporal and spatial nuances of human flow patterns. Notably, this study innovatively incorporates migration, weather, and epidemic data into machine-learning models for feature extraction. Moreover, it introduces weighted factors—\u0000<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>g</mi>\u0000 <mi>r</mi>\u0000 <mi>o</mi>\u0000 <mi>w</mi>\u0000 <mi>t</mi>\u0000 <mi>h</mi>\u0000 <mo>,</mo>\u0000 <mspace></mspace>\u0000 <mi>b</mi>\u0000 <mi>a</mi>\u0000 <mi>s</mi>\u0000 <mi>e</mi>\u0000 <mo>,</mo>\u0000 <mspace></mspace>\u0000 <mi>w</mi>\u0000 <mi>e</mi>\u0000 <mi>e</mi>\u0000 <mi>k</mi>\u0000 </mrow>\u0000 <annotation>$$ growth, base, week $$</annotation>\u0000 </semantics></math>, and \u0000<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>d</mi>\u0000 <mi>a</mi>\u0000 <mi>y</mi>\u0000 </mrow>\u0000 <annotation>$$ day $$</annotation>\u0000 </semantics></math>—to enhance the accuracy of \u0000<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>C</mi>\u0000 <mi>F</mi>\u0000 <mi>I</mi>\u0000 </mrow>\u0000 <annotation>$$ CFI $$</annotation>\u0000 </semantics></math> prediction. Among the combined models, CCFP outperforms others with remarkable scientific precision (root mean squared error, \u0000<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>R</mi>\u0000 <mi>M</mi>\u0000 <mi>S</mi>\u0000 <mi>E</mi>\u0000 <mo>=</mo>\u0000 <mn>2.04</mn>\u0000 </mrow>\u0000 ","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"44 2","pages":"730-752"},"PeriodicalIF":3.4,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cross-Learning With Panel Data Modeling for Stacking and Forecast Time Series Employment in Europe","authors":"Pietro Giorgio Lovaglio","doi":"10.1002/for.3224","DOIUrl":"https://doi.org/10.1002/for.3224","url":null,"abstract":"<p>This paper describes the use of cross-learning with panel data modeling for stacking regressions of different predictive models for time series employment across occupations in Europe during the last 15 years. The ARIMA and state space models were used for the predictions on the first-level model ensemble. On the second level, the time series predictions of these models were combined for stacking, using panel data estimators as a cross-learner and also exploiting the strong hierarchical data structure (time series nested in occupational groups). Very few methods adopt stacking to generate ensembles for time series regressions. Indeed, to the best of our knowledge, panel data modeling has never before been used as a cross-learner in staking strategies. Empirical application was used to fit employment by occupations in 30 European countries between 2010 Q1 and 2022 Q4, using the last year as the test set. The empirical results show that using panel data modeling as a multivariate time series cross-learner that stacks univariate time series base models—especially when they do not produce accurate predictions—is an alternative worthy of consideration, also with respect to such classical aggregation schemes as optimal and equal weighting.</p>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"44 2","pages":"753-780"},"PeriodicalIF":3.4,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/for.3224","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Bias of the ECB Inflation Projections: A State-Dependent Analysis","authors":"Eleonora Granziera,&nbsp;Pirkka Jalasjoki,&nbsp;Maritta Paloviita","doi":"10.1002/for.3236","DOIUrl":"https://doi.org/10.1002/for.3236","url":null,"abstract":"<div>\u0000 \u0000 <p>We test for state-dependent bias in the European Central Bank's inflation projections. We show that the Eurosystem/European Central Bank (ECB) tends to underpredict when the observed inflation rate at the time of forecasting is higher than an estimated threshold of 1.8%. The bias is most pronounced at intermediate forecasting horizons. This suggests that inflation is projected to revert towards the target too quickly. These results cannot be fully explained by the persistence embedded in the forecasting models or by errors in the exogenous assumptions on interest rates, exchange rates, or oil prices. The state-dependent bias may be consistent with the aim of managing inflation expectations, as published forecasts play a central role in the ECB's monetary policy communication strategy.</p>\u0000 </div>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"44 3","pages":"922-940"},"PeriodicalIF":3.4,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143565407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Media Tone: The Role of News and Social Media on Heterogeneous Inflation Expectations","authors":"Joni Heikkinen,&nbsp;Kari Heimonen","doi":"10.1002/for.3225","DOIUrl":"https://doi.org/10.1002/for.3225","url":null,"abstract":"<p>This study investigates the role of media tone on inflation expectations. Examining the relationships between news and the inflation expectations of various US demographic groupings, we find that traditional news influences older cohorts, whereas social media news align more closely with the expectations of younger and more educated groups. Interestingly, social media correspond more closely than traditional news with the expectations of professional forecasters. Our analysis shows that media influences can persist for longer than a year, highlighting the importance of historical inflation data and the gradual adaptation of new information. Additionally, we find that separate media tones for specific news topics such as “Inflation &amp; Fed” and “Healthcare Costs” resonate differently across demographic groups. These insights highlight the nuanced role of media in shaping inflation expectations across demographic segments.</p>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"44 3","pages":"881-921"},"PeriodicalIF":3.4,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/for.3225","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143565253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Forecasting Realized Volatility: The Choice of Window Size","authors":"Yuqing Feng,&nbsp;Yaojie Zhang","doi":"10.1002/for.3221","DOIUrl":"https://doi.org/10.1002/for.3221","url":null,"abstract":"<div>\u0000 \u0000 <p>Different window sizes may produce different empirical results. However, how to choose an ideal window size is still an open question. We investigate how the window size affects the predictive performance of volatility. The empirical results show that the loss function for volatility prediction takes on a U-shape as the window size increases. This suggests that if the window size is chosen too large or too small, the loss function tends to be large and the model's predictive accuracy decreases. A window size of between 1000 and 2000 observations is ideal for various assets because it can produce relatively minimal forecast errors. From an asset allocation perspective, a mean–variance investor can obtain sizeable utility by using a model with a low loss function value for her portfolio. Moreover, the results are robust in a variety of settings.</p>\u0000 </div>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"44 2","pages":"692-705"},"PeriodicalIF":3.4,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Taming Data-Driven Probability Distributions","authors":"Jozef Baruník,&nbsp;Luboš Hanus","doi":"10.1002/for.3208","DOIUrl":"https://doi.org/10.1002/for.3208","url":null,"abstract":"<p>We propose a deep learning approach to probabilistic forecasting of macroeconomic and financial time series. By allowing complex time series patterns to be learned from a data-rich environment, our approach is useful for decision making that depends on the uncertainty of a large number of economic outcomes. In particular, it is informative for agents facing asymmetric dependence of their loss on the outcomes of possibly non-Gaussian and nonlinear variables. We demonstrate the usefulness of the proposed approach on two different datasets where a machine learns patterns from the data. First, we illustrate the gains in predicting stock return distributions that are heavy tailed and asymmetric. Second, we construct macroeconomic fan charts that reflect information from a high-dimensional dataset.</p>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"44 2","pages":"676-691"},"PeriodicalIF":3.4,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/for.3208","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ensemble Multitask Prediction of Air Pollutants Time Series: Based on Variational Inference, Data Projection, and Generative Adversarial Network","authors":"Kang Wang,&nbsp;Chao Qu,&nbsp;Jianzhou Wang,&nbsp;Zhiwu Li,&nbsp;Haiyan Lu","doi":"10.1002/for.3218","DOIUrl":"https://doi.org/10.1002/for.3218","url":null,"abstract":"<div>\u0000 \u0000 <p>In light of the mounting environmental pressures, especially the significant threat urban air pollution poses to public health, there arises an imperative need to develop a data-driven model for air pollution prediction. However, contemporary deep learning techniques, such as recurrent neural networks, often struggle to effectively capture the underlying data patterns and distributions, resulting in reduced model stability. To address this gap, this study introduces an ensemble Wasserstein generative adversarial network framework (EWGF) to enhance the stability and accuracy of PM_2.5 predictions by facilitating the acquisition of more informative data representations through Wasserstein generative adversarial network. The framework contains an intricate feature extraction pipeline that automatically learns features containing residual information as representations of potential features, effectively ameliorating the underutilization of feature information. We address a nonconvex multi-objective optimization problem associated with amalgamating diverse Wasserstein generative adversarial network architectures, which enhance the inherent instability of the predictions. Furthermore, an adaptive search strategy is introduced to ascertain the optimal distribution of prediction residuals, thereby expanding the prediction interval estimation method based on residual distribution. We rigorously evaluate the proposed framework using datasets from three major Indian cities, and our experiments unequivocally show that the EWGF outperforms existing solutions in both PM_2.5 point prediction and interval prediction, evidenced by an approximate 8.07% reduction in mean absolute percentage error and an approximate 19.41% improvement in prediction interval score compared to the baseline model.</p>\u0000 </div>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"44 2","pages":"646-675"},"PeriodicalIF":3.4,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143116411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Vector SHAP Values for Machine Learning Time Series Forecasting","authors":"Ji Eun Choi,&nbsp;Ji Won Shin,&nbsp;Dong Wan Shin","doi":"10.1002/for.3220","DOIUrl":"https://doi.org/10.1002/for.3220","url":null,"abstract":"<div>\u0000 \u0000 <p>We propose a new vector SHapley Additive exPlanations (SHAP) to interpret machine learning models for forecasting time series using lags of predictor variables. Unlike the standard SHAP measuring the contribution of each lag of each predictor variable, the proposed vector SHAP measures the contribution of the vector of the lags of each variable. The vector SHAP has an advantage of faster computation over the standard SHAP. Some desirable properties of the vector SHAP (vector local accuracy, vector missingness, and vector consistency) are established. A Monte Carlo simulation shows that the vector SHAP has a much faster computing time than the SHAP; the difference of the standard SHAP and the vector SHAP is small; the sampling SHAP is sensitive to the sampling proportion in a range of practical application; the vector SHAP mitigates the sensitivity issue. The vector SHAP is applied to the realized volatility of world major stock price indices of 16 countries for forecasting the realized volatility of South Korea stock price index, KOSPI. Further vectoring by regions of Europe, North America, and Asia yields vector SHAP value for each region which is very close to the sum of vector SHAP values of the countries of the region, illustrating usefulness of the strategy of vectoring.</p>\u0000 </div>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"44 2","pages":"635-645"},"PeriodicalIF":3.4,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143116444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Time-Varying US Government Spending Anticipation in Real Time","authors":"Pascal Goemans,&nbsp;Robinson Kruse-Becher","doi":"10.1002/for.3234","DOIUrl":"https://doi.org/10.1002/for.3234","url":null,"abstract":"<p>Due to legislation and implementation lags, forward-looking economic agents anticipate changes in fiscal policy variables before they actually occur. The literature shows that this foresight poses a challenge to the econometric analysis of fiscal policies. While most of the literature uses fully revised data to investigate the degree of fiscal foresight, we use forecasts from the Survey of Professional Forecasters (SPF), the Greenbook/Tealbook from the Federal Reserve, and the Real-Time Data Set for Macroeconomists. Furthermore, we distinguish between federal as well as state and local consumption &amp; investment expenditures. We find that real-time data matter. Using the first release, the SPF nowcast was able to predict 43% of the out-of-sample fluctuation in federal government spending growth (only 24% using the most recent release). Moreover, the SPF was able to predict 60% and 52% of the cumulated growth in federal and state &amp; local government spending growth over a 1-year horizon. We use the Diebold–Mariano tests and model confidence sets to investigate whether SPF forecasts significantly outperform the Greenbook projections and forecasts from purely backward-looking time series models. Compared to the SPF and Greenbook projections, the time series models perform inferior at most forecast horizons. In addition, so-called information advantage regressions reveal that most forecasts could be improved by using the information of the SPF. Using rolling windows, we document remarkable time-variation in the degree of fiscal foresight of the SPF and its information advantage against (augmented) autoregressive models and the Greenbook. Particularly during the 1980s and 2000s, we find a strong degree of anticipation for government spending at the federal level by the SPF and the central bank.</p>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"44 3","pages":"867-880"},"PeriodicalIF":3.4,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/for.3234","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143565423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sectoral Corporate Profits and Long-Run Stock Return Volatility in the United States: A GARCH-MIDAS Approach","authors":"Afees Salisu,&nbsp;Kazeem O. Isah,&nbsp;Ahamuefula Ephraim Ogbonna","doi":"10.1002/for.3207","DOIUrl":"https://doi.org/10.1002/for.3207","url":null,"abstract":"<p>This study aims to examine the usefulness of corporate profits in predicting the return volatility of sectoral stocks in the United States. We use a GARCH-MIDAS approach to keep the datasets in their original frequencies. The results show a consistently positive slope coefficient across various sectoral stocks. This implies that higher profits lead to increased trading of stocks and, subsequently, a higher volatility in the long run than usual. Furthermore, the analysis also extends to predictability beyond the in-sample. We find strong evidence that corporate profits can predict the out-of-sample long-run return volatility of sectoral stocks in the United States. These findings are significant for investors and portfolio managers.</p>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"44 2","pages":"623-634"},"PeriodicalIF":3.4,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/for.3207","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143115485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}