Author
Evangelos Spiliotis
Other affiliations: University of Nicosia, National and Kapodistrian University of Athens
Bio: Evangelos Spiliotis is an academic researcher from National Technical University of Athens. The author has contributed to research in topics: Computer science & Time series. The author has an hindex of 13, co-authored 48 publications receiving 1370 citations. Previous affiliations of Evangelos Spiliotis include University of Nicosia & National and Kapodistrian University of Athens.
Papers
More filters
TL;DR: It is found that the post-sample accuracy of popular ML methods are dominated across both accuracy measures used and for all forecasting horizons examined, and that their computational requirements are considerably greater than those of statistical methods.
Abstract: Machine Learning (ML) methods have been proposed in the academic literature as alternatives to statistical ones for time series forecasting. Yet, scant evidence is available about their relative performance in terms of accuracy and computational requirements. The purpose of this paper is to evaluate such performance across multiple forecasting horizons using a large subset of 1045 monthly time series used in the M3 Competition. After comparing the post-sample accuracy of popular ML methods with that of eight traditional statistical ones, we found that the former are dominated across both accuracy measures used and for all forecasting horizons examined. Moreover, we observed that their computational requirements are considerably greater than those of statistical methods. The paper discusses the results, explains why the accuracy of ML models is below that of statistical ones and proposes some possible ways forward. The empirical results found in our research stress the need for objective and unbiased ways to test the performance of forecasting methods that can be achieved through sizable and open competitions allowing meaningful comparisons and definite conclusions.
800 citations
TL;DR: All aspects of M4 are covered in detail, including its organization and running, the presentation of its results, the top-performing methods overall and by categories, its major findings and their implications, and the computational requirements of the various methods.
507 citations
TL;DR: The M4 competition is the continuation of three previous competitions started more than 45 years ago whose purpose was to learn how to improve forecasting accuracy, and how such learning can be applied to advance the theory and practice of forecasting.
407 citations
Repository•
Polytechnic University of Turin1, National Technical University of Athens2, KEDGE Business School3, University of Birmingham4, University of Mons5, Monash University6, University of Southampton7, Lancaster University8, University of Glasgow9, University of Brescia10, University of Oxford11, Zürcher Fachhochschule12, University of Reading13, University of Lisbon14, University of the Algarve15, Pontifical Catholic University of Rio de Janeiro16, Ghent University17, Nicolaus Copernicus University in Toruń18, Erasmus University Rotterdam19, SAS Institute20, University of Bath21, University of Padua22, University of Virginia23, Bocconi University24, MODUL University Vienna25, University of Maryland, College Park26, University College London27, Amazon.com28, KAIST29, Georgetown University30, Beihang University31, Miami University32, University of Skövde33, Central University of Finance and Economics34, Manchester Metropolitan University35, University of Nicosia36, United States Department of the Treasury37, George Washington University38, Durham University39, Australian National University40, University College Dublin41, University of Sydney42, University of Thessaly43, University of Valencia44, University of Bristol45, University of Castilla–La Mancha46, Technical University of Denmark47, Polytechnic Institute of Porto48, Saint Louis University49, Cardiff University50, Warsaw School of Economics51, Macquarie University52, University of Moratuwa53, University of Sri Jayewardenepura54, International Institute of Minnesota55, National and Kapodistrian University of Athens56, Norwegian Computing Center57, University of Bologna58, Duke University59, University of Duisburg-Essen60
TL;DR: A non-systematic review of the theory and the practice of forecasting, offering a wide range of theoretical, state-of-the-art models, methods, principles, and approaches to prepare, produce, organise, and evaluate forecasts.
Abstract: Forecasting has always been at the forefront of decision making and planning. The uncertainty that surrounds the future is both exciting and challenging, with individuals and organisations seeking to minimise risks and maximise utilities. The large number of forecasting applications calls for a diverse set of forecasting methods to tackle real-life challenges. This article provides a non-systematic review of the theory and the practice of forecasting. We provide an overview of a wide range of theoretical, state-of-the-art models, methods, principles, and approaches to prepare, produce, organise, and evaluate forecasts. We then demonstrate how such theoretical concepts are applied in a variety of real-life contexts.
We do not claim that this review is an exhaustive list of methods and applications. However, we wish that our encyclopedic presentation will offer a point of reference for the rich work that has been undertaken over the last decades, with some key insights for the future of forecasting theory and practice. Given its encyclopedic nature, the intended mode of reading is non-linear. We offer cross-references to allow the readers to navigate through the various topics. We complement the theoretical concepts and applications covered by large lists of free or open-source software implementations and publicly-available databases.
163 citations
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.
129 citations
Cited by
More filters
01 Jan 2006
TL;DR: Probability distributions of linear models for regression and classification are given in this article, along with a discussion of combining models and combining models in the context of machine learning and classification.
Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.
10,141 citations
01 Jan 2016
TL;DR: The modern applied statistics with s is universally compatible with any devices to read, and is available in the digital library an online access to it is set as public so you can download it instantly.
Abstract: Thank you very much for downloading modern applied statistics with s. As you may know, people have search hundreds times for their favorite readings like this modern applied statistics with s, but end up in harmful downloads. Rather than reading a good book with a cup of coffee in the afternoon, instead they cope with some harmful virus inside their laptop. modern applied statistics with s is available in our digital library an online access to it is set as public so you can download it instantly. Our digital library saves in multiple countries, allowing you to get the most less latency time to download any of our books like this one. Kindly say, the modern applied statistics with s is universally compatible with any devices to read.
5,249 citations
TL;DR: DeepAR is proposed, a methodology for producing accurate probabilistic forecasts, based on training an auto regressive recurrent network model on a large number of related time series, with accuracy improvements of around 15% compared to state-of-the-art methods.
726 citations
Book•
01 Jan 1989
TL;DR: A critical review of influential closed-loop supply chain research that takes a business economics perspective can be found in this article, where the authors offer a critical review and analysis of influential CLSC research.
Abstract: Research in closed-loop supply chains (CLSCs) has grown rapidly over the last 10 years. The authors offer a critical review of influential CLSC research that takes a business economics perspective. Much of the research was inspired by practice-driven thoughtpieces, and this helped to keep research focused on relevant issues. However, CLSC research has several assumptions, such as perfect substitution between new and remanufactured products that risk becoming institutionalized. There is a strong need to carefully examine current industrial practice so that research remains focused on relevant problems. Deeper understanding of consumer perceptions of remanufactured products, product diffusion, and valuation of returned products are needed for the field to continue to add insights into developing sustainable economies.
711 citations