Showing papers in "International Journal of Forecasting in 2022"

TL;DR: The M5 Accuracy Challenge as discussed by the authors was the first of two parallel challenges in the latest M competition with the aim of advancing the theory and practice of forecasting, and the main objective was to accurately predict 42,840 time series representing the hierarchical unit sales for the largest retail company in the world by revenue, Walmart.

TL;DR: In this paper , the authors provide an overview of a wide range of theoretical, state-of-the-art models, methods, principles, and approaches to prepare, produce, organize, and evaluate forecasts.

TL;DR: In this paper , the authors consider the consequences of multiple dimensions of impact so as to continuously calibrate predictive insights and decision-making, when major decisions are based on forecasts, the harms (in terms of health, economy, and society at large) and the asymmetry of risks need to be approached in a holistic fashion, considering the totality of the evidence.

TL;DR: In this article , the authors document and evaluate how businesses are reacting to the COVID-19 crisis through August 2020 and find that a greater share of firms report significant or severe disruptions to sales activity than to supply chains.

TL;DR: The authors reviewed the research literature on forecasting retail demand, from the strategic to the operational, as sales are aggregated over products to stores and to the company overall, and concluded that although causal models outperform simple benchmarks, adequate evidence on machine learning methods has not yet accumulated.

TL;DR: This article proposed a text-based forecasting framework, which can effectively identify and quantify factors affecting agricultural futures based on massive online news headlines, and empirically tested the proposed framework is empirically test at forecasting soybean futures prices in the Chinese market.

TL;DR: In this paper , a hybrid ensemble forecasting methodology that integrating empirical mode decomposition (EMD), long short-term memory (LSTM) and extreme learning machine (ELM) is proposed for the monthly biofuel (a typical agriculture-related energy) production based on the principle of decomposition-reconstruction-ensemble.

TL;DR: In this paper , Wang et al. used machine learning from both variable selection and common factor perspectives to improve the predictability of aggregate oil market volatility with a substantially large macroeconomic database, including 127 macro variables.

TL;DR: A systematic review of ground-based sky image-based intra-hour solar forecasting (GSI-IHSF) is presented in this paper , where the authors propose a generic framework consisting of four modules, i.e., sky image acquisition, sky image preprocessing, cloud forecasting, and solar forecasting.

TL;DR: The Accuracy and Uncertainty Forecasting Competition (M5) as mentioned in this paper focused on a retail sales forecasting application with the objective to produce the most accurate point forecasts for 42,840 time series that represent the hierarchical unit sales of the largest retail company in the world, Walmart.

TL;DR: In this article , the conditional intensity of new COVID-19 cases and deaths in the U.S. at the county level, estimating the dynamic reproduction number of the virus within an EM algorithm through a regression on Google mobility indices and demographic covariates.

TL;DR: In this article , the authors have published real-time forecasts of confirmed cases and deaths from coronavirus disease 2019 (COVID-19) since mid-March 2020, which are short-term statistical extrapolations of past and current data.

TL;DR: In this paper , a statistical, time series approach is proposed to model and predict the short-term behavior of COVID-19 outbreaks, which assumes a multiplicative trend, aiming to capture the continuation of the two variables (global confirmed cases and deaths) as well as their uncertainty.

TL;DR: The authors provides an up-to-date review of the extensive literature on forecast combinations and a reference to available open-source software implementations, highlighting the potential and limitations of various methods and highlighting how these ideas have developed over time.

TL;DR: The authors consider simple methods to improve the growth nowcasts and forecasts obtained by mixed-frequency MIDAS and UMIDAS models with a variety of indicators during the Covid-19 crisis and recovery period, such as combining forecasts across various specifications for the same model and/or across different models.

TL;DR: In this paper , a forecast combination approach based on a global optimization method, called the Artificial Bee Colony Algorithm (ABC), for forecasting soybean and corn futures prices is proposed.

TL;DR: The M5 uncertainty competition as discussed by the authors was the second parallel challenge of the latest M competition, aiming to advance the theory and practice of forecasting, and the particular objective of this competition was to accurately forecast the uncertainty distributions of the realized values of 42,840 time series that represent the hierarchical unit sales of the largest retail company in the world by revenue, Walmart.

TL;DR: In this article , a new combination approach based on principal component analysis (PCA) is proposed to improve the predictability of crude oil futures market returns, which combines individual forecasts given by all PCA subset regression models that use all potential predictor subsets to construct PCA indexes.

TL;DR: In this article , the authors developed a new dynamic model that is able to account for long memory and asymmetries in the volatility process, as well as for the presence of time-varying skewness and kurtosis.

TL;DR: In this article , the authors extend the quarterly growth-at-risk (GaR) approach of Adrian et al. (2019) by accounting for the high-frequency nature of financial conditions indicators.

TL;DR: In this article , a set of HAR models with three types of infinite Hidden Markov regime-switching structures were constructed, and the forecast performance was evaluated using both statistical and economic evaluation measures.

TL;DR: The prevalence of gradient boosted trees among the top contestants in the M5 competition is potentially the most eye-catching result as discussed by the authors , where tree-based methods out-shone other solutions, in particular deep learning-based solutions.

TL;DR: The U.S. COVID-19 Forecast Hub aggregates forecasts of the short-term burden of COVID19 in the United States from many contributing teams as discussed by the authors .

TL;DR: In this paper , a simple recency heuristic was used to predict the proportion of flu-related doctor visits in a given week to the proportion from the most recent week, based on psychological theory of how people deal with rapidly changing situations.

TL;DR: In this article , the authors conducted a structured literature search in Scopus, Web of Science, ABI Inform, and Google Scholar to identify what has been done so far, and where are the needs for further research.

TL;DR: This paper introduced two indicators of topic and sentiment for the short and sparse text data to tackle the issue of mismatch between the short text and the topic model and further affecting the forecasting performance.

TL;DR: In this article , the authors discuss common errors and fallacies when using naive empiricism and point forecasts for fat-tailed variables, as well as the insufficiency of using naive first-order scientific methods for tail risk management.

TL;DR: In this article , the authors analyzed a diverse set of COVID-19 forecast algorithms, including several modifications of NIPA, and showed that network-based forecasting is superior to any other forecasting algorithm.

TL;DR: Wang et al. as discussed by the authors developed a dictionary-based sentiment analysis method to convert the textual review concerning each attribute of the product into the corresponding sentiment score by combining the prospect theory and relevant online review data, sentiment indices in each period are calculated.

TL;DR: In this article , an aligned global economic policy uncertainty (GEPU) index based on a modified machine learning approach is proposed to predict crude oil market volatility both in- and out-of-sample.