Journal of Forecasting最新文献

Robust Real-Time Estimates of the German Output Gap Based on a Multivariate Trend-Cycle Decomposition 基于多元趋势周期分解的德国产出缺口稳健实时估计

IF 2.7 3区经济学

Journal of Forecasting Pub Date : 2026-03-03 Epub Date: 2025-12-12 DOI: 10.1002/for.70079

Tino Berger, Christian Ochsner

引用次数: 0

Data-Driven Prediction of Climate Variables in Agricultural Cities of India With Hybrid GA-TCN-LSTM Model 基于GA-TCN-LSTM混合模型的印度农业城市气候变量数据驱动预测

IF 2.7 3区经济学

Journal of Forecasting Pub Date : 2026-03-03 Epub Date: 2025-12-16 DOI: 10.1002/for.70088

Anil Utku

{"title":"Data-Driven Prediction of Climate Variables in Agricultural Cities of India With Hybrid GA-TCN-LSTM Model","authors":"Anil Utku","doi":"10.1002/for.70088","DOIUrl":"https://doi.org/10.1002/for.70088","url":null,"abstract":"<div>\u0000 \u0000 <p>Accurate prediction of climate variables is important in reducing the effects of natural disasters and taking preventive measures for agriculture and food security, energy sector, public health, and water resources management. For agricultural production, it is essential for producers to determine strategies for their agricultural activities and to increase agricultural productivity. Issues such as determining planting and harvest times, determining pesticides to be used against agricultural pests, selecting products to be planted, irrigation, and sustainable agriculture are directly related to climate variables. In this study, a GA-TCN-LSTM hybrid prediction model was created to determine climate variables such as relative humidity, temperature, wind speed, and dew point in Bhopal, Indore, Kanpur, Ludhiana, and Patna, which are among the prominent cities of India in terms of agricultural production. The hyper-parameters of the developed model using the temporal convolutional networks (TCN) and long short-term memory (LSTM) were optimized with the genetic algorithm (GA), and the GA-TCN-LSTM hybrid model was created. GA-TCN-LSTM was extensively compared with the base TCN-LSTM, convolutional neural network (CNN), LSTM, TCN, and CNN-LSTM. The compared models were tested using approximately 15 years of hourly, up-to-date, and real-time data of the cities. Experiments showed that GA-TCN-LSTM outperformed the compared models and had above 0.9 R-Squared (R<sup>2</sup>) for the majority of cities and climate variables.</p>\u0000 </div>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"45 3","pages":"1225-1244"},"PeriodicalIF":2.7,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147566071","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}

引用次数: 0

GDP Nowcasting With Artificial Neural Networks: How Much Does Long-Term Memory Matter? 用人工神经网络预测GDP：长期记忆有多重要？

IF 2.7 3区经济学

Journal of Forecasting Pub Date : 2026-03-03 Epub Date: 2025-11-23 DOI: 10.1002/for.70061

Kristóf Németh, Dániel Hadházi

{"title":"GDP Nowcasting With Artificial Neural Networks: How Much Does Long-Term Memory Matter?","authors":"Kristóf Németh, Dániel Hadházi","doi":"10.1002/for.70061","DOIUrl":"https://doi.org/10.1002/for.70061","url":null,"abstract":"<div>\u0000 \u0000 <p>We apply artificial neural networks (ANNs) to nowcast quarterly GDP growth for the US economy. Using the monthly FRED-MD database, we compare the nowcasting performance of five different ANN architectures: the multilayer perceptron (MLP), the one-dimensional convolutional neural network (1D CNN), the Elman recurrent neural network (RNN), the long short-term memory (LSTM) network, and the gated recurrent unit (GRU). The empirical analysis presents results from two distinctively different evaluation periods. The first (2012:Q1–2019:Q4) is characterized by balanced economic growth, while the second (2012:Q1–2024:Q2) also includes periods of the COVID-19 recession. During the first evaluation period, longer input sequences slightly improve nowcasting performance for some ANNs, but the best accuracy is still achieved with 8-month-long input sequences at the end of the nowcasting window. Results from the second test period depict the role of long-term memory even more clearly. The MLP, the 1D CNN, and the Elman RNN work best with 8-month-long input sequences at each step of the nowcasting window. The relatively weak performance of the gated RNNs also suggests that architectural features enabling long-term memory do not result in more accurate nowcasts for GDP growth. The combined results indicate that the 1D CNN seems to represent a “sweet spot” between the simple time-agnostic MLP and the more complex (gated) RNNs. The network generates nearly as accurate nowcasts as the best competitor for the first test period, while it achieves the overall best accuracy during the second evaluation period. Consequently, as a first in the literature, we propose the application of the 1D CNN for economic nowcasting.</p>\u0000 </div>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"45 3","pages":"924-963"},"PeriodicalIF":2.7,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147568597","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}

引用次数: 0

Combined Effects of Fat-Tail and Spread Forecasting on Pairs Trading: A Hybrid Model Based on Integrating VAR With GRU Models 粗尾与价差预测对配对交易的联合效应：基于VAR与GRU模型集成的混合模型

IF 2.7 3区经济学

Journal of Forecasting Pub Date : 2026-03-03 Epub Date: 2025-12-12 DOI: 10.1002/for.70074

Yuhee Kwon, Youngsoo Choi

{"title":"Combined Effects of Fat-Tail and Spread Forecasting on Pairs Trading: A Hybrid Model Based on Integrating VAR With GRU Models","authors":"Yuhee Kwon, Youngsoo Choi","doi":"10.1002/for.70074","DOIUrl":"https://doi.org/10.1002/for.70074","url":null,"abstract":"<p>Pairs trading, a popular algorithmic trading strategy, exploits the short-term price difference (spread) between two comoving assets. Empirically, the spread distribution of most assets in pairs trading has a fat-tail characteristic that does not follow a normal distribution. However, existing trading strategies did not consider these characteristics and attempted to improve performance by applying complex machine learning techniques. This paper targets cryptocurrency assets that show the fat-tail characteristics of the spread distribution well due to their high volatility and presents a new hybrid model that can solve these characteristics in machine learning, namely, VAR-GRU-QT (Vector AutoRegression–Gated Recurrent Unit–Quantile Transform). The VAR-GRU model is proposed for spread prediction, whereas the QT-based pair trading strategy seeks to capture trading signals. The empirical analysis results show that the VAR-GRU-QT model improves prediction performance over the comparative model and significantly improves pairs trading performance. In addition, it was confirmed that as the threshold of the trading signal increases, the fat-tail effect appears more prominently in the hybrid model. In conclusion, by considering the non-Gaussian distribution of the spread, the prediction accuracy of the hybrid model is improved, and by additionally applying the quantile-based trading methodology, the trading performance of the pair trading strategy is significantly improved over the comparative model.</p>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"45 3","pages":"1110-1128"},"PeriodicalIF":2.7,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/for.70074","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147565227","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}

引用次数: 0

Risk Spillover Network in Commodity Markets Under Climate Transition Risk 气候转型风险下商品市场的风险溢出网络

IF 2.7 3区经济学

Journal of Forecasting Pub Date : 2026-03-03 Epub Date: 2025-12-01 DOI: 10.1002/for.70072

Zhihong Niu, Yan Wang

{"title":"Risk Spillover Network in Commodity Markets Under Climate Transition Risk","authors":"Zhihong Niu, Yan Wang","doi":"10.1002/for.70072","DOIUrl":"https://doi.org/10.1002/for.70072","url":null,"abstract":"<div>\u0000 \u0000 <p>The article constructs a connectivity network based on the dynamic conditional correlation generalized autoregressive conditional heteroskedasticity (DCC-GARCH) model and spillover index method, systematically revealing the risk contagion effects within China's commodity markets under the context of climate transition. In the long run, the energy and chemical markets act as risk spillover transmitters in the commodity system, while the metal and agricultural markets function as risk receivers. Gold typically passively absorbs risk spillovers from other markets during risk events, presenting a structure of “receiving more and spilling less.” However, in the short term, the risk roles of markets undergo shifts in response to changes in macroeconomic conditions. The risk roles of different markets exhibit significant time-varying characteristics, and the network structure experiences dynamic reconstruction under the impact of specific events. In terms of policy recommendations, for spillover industries, it is crucial to promptly identify potential systemic risk sources to prevent high-carbon industries from generating transition risks. For risk-receiving industries, their risk-mitigating role during market turbulence should be fully utilized. Additionally, attention should be given to the potential risks associated with the transformation of risk roles during extreme events or changes in macroeconomic policies.</p>\u0000 </div>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"45 3","pages":"1036-1051"},"PeriodicalIF":2.7,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147562403","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}

引用次数: 0

Mortality Forecasting Using Variational Inference 用变分推理预测死亡率

IF 2.7 3区经济学

Journal of Forecasting Pub Date : 2026-03-03 Epub Date: 2025-12-05 DOI: 10.1002/for.70078

Patrik Andersson, Mathias Lindholm

引用次数: 0

Exploiting Functional Time Series Prediction for PM2.5 Based on Multivariate Variational Mode Decomposition and Anomaly Detection 基于多元变分模态分解和异常检测的PM2.5函数时间序列预测

IF 2.7 3区经济学

Journal of Forecasting Pub Date : 2026-03-03 Epub Date: 2025-12-09 DOI: 10.1002/for.70075

Zhifu Tao, Weiying Liu, Qin Xu, Piao Wang

{"title":"Exploiting Functional Time Series Prediction for PM2.5 Based on Multivariate Variational Mode Decomposition and Anomaly Detection","authors":"Zhifu Tao, Weiying Liu, Qin Xu, Piao Wang","doi":"10.1002/for.70075","DOIUrl":"https://doi.org/10.1002/for.70075","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper presents a novel approach to high-frequency time series forecasting in the context of functional time series, addressing challenges such as data complexity and outliers. The proposed hybrid model integrates outlier detection, multivariate variational mode decomposition (MVMD), and model pooling to enhance forecasting accuracy. Initially, outliers are identified using the isolation forest technique and subsequently replaced with smoothed values via a sliding window moving average. MVMD is then employed to decompose the time series into high-, mid-, and low-frequency components, based on sample entropy. Discrete daily observations are transformed into functional data using Fourier basis functions, and functional principal component analysis (FPCA) is applied for dimensionality reduction, generating principal component scores and functions. Forecasting is carried out through model pooling, which combines statistical, machine learning, and deep learning techniques to predict the principal component scores. The final prediction is obtained by aggregating the forecasts of the predicted scores and their corresponding principal component functions. Empirical results, based on PM2.5 forecasting, demonstrate that the proposed approach significantly outperforms alternative models, offering valuable contributions to air quality monitoring and informed decision-making.</p>\u0000 </div>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"45 3","pages":"1077-1091"},"PeriodicalIF":2.7,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147564167","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}

引用次数: 0

Obtaining Conservative Assessments of Profitability for Current Period Based on Target-Adjusted Achievable Capacity Index With SARIMA Prediction 基于SARIMA预测的目标调整可达产能指数的当期盈利能力保守评估

IF 2.7 3区经济学

Journal of Forecasting Pub Date : 2026-03-03 Epub Date: 2025-12-15 DOI: 10.1002/for.70085

Rung-Hung Su, Yi-Hung Kung, Yi-Hung Lee

{"title":"Obtaining Conservative Assessments of Profitability for Current Period Based on Target-Adjusted Achievable Capacity Index With SARIMA Prediction","authors":"Rung-Hung Su, Yi-Hung Kung, Yi-Hung Lee","doi":"10.1002/for.70085","DOIUrl":"https://doi.org/10.1002/for.70085","url":null,"abstract":"<div>\u0000 \u0000 <p>The achievable capacity index (ACI) is an effective tool for measuring and estimating the profitability of a single-period product, where profitability is the probability of achieving a target profit under optimal ordering quantity. Setting a reasonable target profit (or corresponding target demand) is crucial, as it can impact profitability measurements and result in misguided decision-making for the next period, especially when demand fluctuates over time. This study applies the seasonal autoregressive integrated moving average (SARIMA) to time-series data to account for time dependencies in predicting target demand for the next period. We then developed a new ACI, referred to as t-ACI, which incorporates the predicted target demand. In estimating the t-ACI, we may encounter the risk of overestimation due to sampling error. Therefore, we derived the lower confidence bound for the t-ACI (LCBtA) to provide a conservative assessment of profitability. Finally, we explore the conservative profitability evaluation using LCBtA to identify profitable products. Some generic tables and procedures of decision-making for evaluation are provided. Regarding insights and implications, variations in Type-I errors for prediction and estimation significantly influence the direction of decision-making in evaluations. For instance, increasing the Type-I error for estimation or decreasing it for prediction can positively steer the evaluation.</p>\u0000 </div>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"45 3","pages":"1145-1157"},"PeriodicalIF":2.7,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147565969","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}

引用次数: 0

Data-Driven Prediction of Climate Variables in Agricultural Cities of India With Hybrid GA-TCN-LSTM Model 基于GA-TCN-LSTM混合模型的印度农业城市气候变量数据驱动预测

IF 2.7 3区经济学

Journal of Forecasting Pub Date : 2026-03-03 Epub Date: 2025-12-16 DOI: 10.1002/for.70088

Anil Utku

{"title":"Data-Driven Prediction of Climate Variables in Agricultural Cities of India With Hybrid GA-TCN-LSTM Model","authors":"Anil Utku","doi":"10.1002/for.70088","DOIUrl":"https://doi.org/10.1002/for.70088","url":null,"abstract":"<div>\u0000 \u0000 <p>Accurate prediction of climate variables is important in reducing the effects of natural disasters and taking preventive measures for agriculture and food security, energy sector, public health, and water resources management. For agricultural production, it is essential for producers to determine strategies for their agricultural activities and to increase agricultural productivity. Issues such as determining planting and harvest times, determining pesticides to be used against agricultural pests, selecting products to be planted, irrigation, and sustainable agriculture are directly related to climate variables. In this study, a GA-TCN-LSTM hybrid prediction model was created to determine climate variables such as relative humidity, temperature, wind speed, and dew point in Bhopal, Indore, Kanpur, Ludhiana, and Patna, which are among the prominent cities of India in terms of agricultural production. The hyper-parameters of the developed model using the temporal convolutional networks (TCN) and long short-term memory (LSTM) were optimized with the genetic algorithm (GA), and the GA-TCN-LSTM hybrid model was created. GA-TCN-LSTM was extensively compared with the base TCN-LSTM, convolutional neural network (CNN), LSTM, TCN, and CNN-LSTM. The compared models were tested using approximately 15 years of hourly, up-to-date, and real-time data of the cities. Experiments showed that GA-TCN-LSTM outperformed the compared models and had above 0.9 R-Squared (R<sup>2</sup>) for the majority of cities and climate variables.</p>\u0000 </div>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"45 3","pages":"1225-1244"},"PeriodicalIF":2.7,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147566202","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}

引用次数: 0

The Impact of News Sentiment on the Bitcoin Price via Machine Learning and Deep Learning-Based NLP Models 通过机器学习和基于深度学习的NLP模型研究新闻情绪对比特币价格的影响

IF 2.7 3区经济学

Journal of Forecasting Pub Date : 2026-03-03 Epub Date: 2025-11-20 DOI: 10.1002/for.70068

Yunus Emre Gür, Emre Ünal

{"title":"The Impact of News Sentiment on the Bitcoin Price via Machine Learning and Deep Learning-Based NLP Models","authors":"Yunus Emre Gür, Emre Ünal","doi":"10.1002/for.70068","DOIUrl":"https://doi.org/10.1002/for.70068","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper employs deep learning and machine learning-based NLP models to investigate the impact of the news sentiment on the Bitcoin price. The lagged Bitcoin variables, news indicators, macroeconomic, and financial factors were taken into account to explain the importance of news sentiment on the Bitcoin price. Moreover, FinBERT-based sentiment scores and semantic features extracted from over 650,000 financial news headlines were integrated with financial and macroeconomic variables. The importance scores of the investigation showed that Bitcoin was largely explained by its lagged price movements, which suggests the speculative nature of the cryptocurrency. However, the investigation also revealed that Bitcoin was significantly influenced by the news sentiment score. In other words, the paper indicates that the movements in the Bitcoin price can be predominantly explained by the news sentiment. Advanced hybrid models (all ML and DL models with the addition of variables obtained with the FinBERT model) were optimized using Optuna and RandomizedSearchCV. The FinBERT-LSTM model achieved the best prediction accuracy. Nevertheless, the main findings indicated that the response of the Bitcoin price to negative news was much stronger than to positive and neutral news. This finding suggests that the asymmetric relationship between the Bitcoin price and news sentiment was evident. GARCH-based volatility and what-if scenario analyses further demonstrated that negative sentiment leads to sharper fluctuations in the Bitcoin price. The paper provides important implications for policymakers, portfolio managers, investors, and academics.</p>\u0000 </div>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":"45 3","pages":"895-923"},"PeriodicalIF":2.7,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147567728","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}

引用次数: 0