Interval time series forecasting: A systematic literature review

作者：Piao Wang, Shahid Hussain Gurmani, Zhifu Tao, Jinpei Liu, Huayou Chen · 发表于：Journal of Forecasting · 年份：2023 · DOI：10.1002/for.3024 · 被引用次数：29 · 研究领域：Stock Market Forecasting Methods、Time Series Analysis and Forecasting、Forecasting Techniques and Applications

Abstract Interval time series forecasting can be used for forecasting special symbolic data comprising lower and upper bounds and plays an important role in handling the complexity, instability, and uncertainty of observed objects. The purpose of this research is to identify the most widely used definition of interval time series; classify existing research into mature research, current research focus, and research gaps within the defined framework; and recommend future directions for interval forecasting research. To achieve this goal, we have conducted a systematic literature review, comprising search strategy planning, screening mechanism determination, document analysis, and report generation. During the search strategy planning stage, eight literature search libraries are selected to obtain the most extensive studies (total of 525 targets). In the screening‐mechanism determination stage, through the inclusion and exclusion mechanism, the literature that is repetitive, of low‐relevance, and from other fields are discarded, and 125 studies are finally selected. In the document analysis stage, tag‐based methods and classification grids are selected to analyze the shortlisted studies. The results show that there are still numerous research gaps in interval time series forecasting, such as the establishment of hybrid models, application of multisource information, development and application of evaluation techniques, and expansion of application scenarios. In the report‐gener...