Slawek Smyl , Christoph Bergmeir , Alexander Dokumentov , Xueying Long , Erwin Wibowo , Daniel Schmidt
{"title":"局部和全局趋势贝叶斯指数平滑模型","authors":"Slawek Smyl , Christoph Bergmeir , Alexander Dokumentov , Xueying Long , Erwin Wibowo , Daniel Schmidt","doi":"10.1016/j.ijforecast.2024.03.006","DOIUrl":null,"url":null,"abstract":"<div><div>This paper describes a family of seasonal and non-seasonal time series models that can be viewed as generalisations of additive and multiplicative exponential smoothing models to model series that grow faster than linear but slower than exponential. Their development is motivated by fast-growing, volatile time series. In particular, our models have a global trend that can smoothly change from additive to multiplicative and is combined with a linear local trend. Seasonality, when used, is multiplicative in our models, and the error is always additive but heteroscedastic and can grow through a parameter sigma. We leverage state-of-the-art Bayesian fitting techniques to fit these models accurately, which are more complex and flexible than standard exponential smoothing models. When applied to the M3 competition data set, our models outperform the best algorithms in the competition and other benchmarks, thus achieving, to the best of our knowledge, the best results of per-series univariate methods on this dataset in the literature. An open-source software package of our method is available.</div></div>","PeriodicalId":14061,"journal":{"name":"International Journal of Forecasting","volume":"41 1","pages":"Pages 111-127"},"PeriodicalIF":6.9000,"publicationDate":"2024-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Local and global trend Bayesian exponential smoothing models\",\"authors\":\"Slawek Smyl , Christoph Bergmeir , Alexander Dokumentov , Xueying Long , Erwin Wibowo , Daniel Schmidt\",\"doi\":\"10.1016/j.ijforecast.2024.03.006\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>This paper describes a family of seasonal and non-seasonal time series models that can be viewed as generalisations of additive and multiplicative exponential smoothing models to model series that grow faster than linear but slower than exponential. Their development is motivated by fast-growing, volatile time series. In particular, our models have a global trend that can smoothly change from additive to multiplicative and is combined with a linear local trend. Seasonality, when used, is multiplicative in our models, and the error is always additive but heteroscedastic and can grow through a parameter sigma. We leverage state-of-the-art Bayesian fitting techniques to fit these models accurately, which are more complex and flexible than standard exponential smoothing models. When applied to the M3 competition data set, our models outperform the best algorithms in the competition and other benchmarks, thus achieving, to the best of our knowledge, the best results of per-series univariate methods on this dataset in the literature. An open-source software package of our method is available.</div></div>\",\"PeriodicalId\":14061,\"journal\":{\"name\":\"International Journal of Forecasting\",\"volume\":\"41 1\",\"pages\":\"Pages 111-127\"},\"PeriodicalIF\":6.9000,\"publicationDate\":\"2024-04-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Forecasting\",\"FirstCategoryId\":\"96\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0169207024000311\",\"RegionNum\":2,\"RegionCategory\":\"经济学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ECONOMICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Forecasting","FirstCategoryId":"96","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0169207024000311","RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ECONOMICS","Score":null,"Total":0}
Local and global trend Bayesian exponential smoothing models
This paper describes a family of seasonal and non-seasonal time series models that can be viewed as generalisations of additive and multiplicative exponential smoothing models to model series that grow faster than linear but slower than exponential. Their development is motivated by fast-growing, volatile time series. In particular, our models have a global trend that can smoothly change from additive to multiplicative and is combined with a linear local trend. Seasonality, when used, is multiplicative in our models, and the error is always additive but heteroscedastic and can grow through a parameter sigma. We leverage state-of-the-art Bayesian fitting techniques to fit these models accurately, which are more complex and flexible than standard exponential smoothing models. When applied to the M3 competition data set, our models outperform the best algorithms in the competition and other benchmarks, thus achieving, to the best of our knowledge, the best results of per-series univariate methods on this dataset in the literature. An open-source software package of our method is available.
期刊介绍:
The International Journal of Forecasting is a leading journal in its field that publishes high quality refereed papers. It aims to bridge the gap between theory and practice, making forecasting useful and relevant for decision and policy makers. The journal places strong emphasis on empirical studies, evaluation activities, implementation research, and improving the practice of forecasting. It welcomes various points of view and encourages debate to find solutions to field-related problems. The journal is the official publication of the International Institute of Forecasters (IIF) and is indexed in Sociological Abstracts, Journal of Economic Literature, Statistical Theory and Method Abstracts, INSPEC, Current Contents, UMI Data Courier, RePEc, Academic Journal Guide, CIS, IAOR, and Social Sciences Citation Index.