Enhancing Predictability Assessment: An Overview and Analysis of Predictability Measures for Time Series and Network Links
Driven by the variety of available measures intended to estimate predictability of diverse objects such as time series and network links, this paper presents a comprehensive overview of the existing literature in this domain. Our overview delves into predictability from two distinct perspectives: th...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/25/11/1542 |
| _version_ | 1797459432782692352 |
|---|---|
| author | Alexandra Bezbochina Elizaveta Stavinova Anton Kovantsev Petr Chunaev |
| author_facet | Alexandra Bezbochina Elizaveta Stavinova Anton Kovantsev Petr Chunaev |
| author_sort | Alexandra Bezbochina |
| collection | DOAJ |
| description | Driven by the variety of available measures intended to estimate predictability of diverse objects such as time series and network links, this paper presents a comprehensive overview of the existing literature in this domain. Our overview delves into predictability from two distinct perspectives: the <i>intrinsic</i> predictability, which represents a data property independent of the chosen forecasting model and serves as the highest achievable forecasting quality level, and the <i>realized</i> predictability, which represents a chosen quality metric for a specific pair of data and model. The reviewed measures are used to assess predictability across different objects, starting from time series (univariate, multivariate, and categorical) to network links. Through experiments, we establish a noticeable relationship between measures of realized and intrinsic predictability in both generated and real-world time series data (with the correlation coefficient being statistically significant at a 5% significance level). The discovered correlation in this research holds significant value for tasks related to evaluating time series complexity and their potential to be accurately predicted. |
| first_indexed | 2024-03-09T16:51:16Z |
| format | Article |
| id | doaj.art-d78e6dbbf2e5407981e31e883f4620df |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-09T16:51:16Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-d78e6dbbf2e5407981e31e883f4620df2023-11-24T14:41:04ZengMDPI AGEntropy1099-43002023-11-012511154210.3390/e25111542Enhancing Predictability Assessment: An Overview and Analysis of Predictability Measures for Time Series and Network LinksAlexandra Bezbochina0Elizaveta Stavinova1Anton Kovantsev2Petr Chunaev3National Center for Cognitive Research, ITMO University, 16 Birzhevaya Lane, Saint Petersburg 199034, RussiaNational Center for Cognitive Research, ITMO University, 16 Birzhevaya Lane, Saint Petersburg 199034, RussiaNational Center for Cognitive Research, ITMO University, 16 Birzhevaya Lane, Saint Petersburg 199034, RussiaNational Center for Cognitive Research, ITMO University, 16 Birzhevaya Lane, Saint Petersburg 199034, RussiaDriven by the variety of available measures intended to estimate predictability of diverse objects such as time series and network links, this paper presents a comprehensive overview of the existing literature in this domain. Our overview delves into predictability from two distinct perspectives: the <i>intrinsic</i> predictability, which represents a data property independent of the chosen forecasting model and serves as the highest achievable forecasting quality level, and the <i>realized</i> predictability, which represents a chosen quality metric for a specific pair of data and model. The reviewed measures are used to assess predictability across different objects, starting from time series (univariate, multivariate, and categorical) to network links. Through experiments, we establish a noticeable relationship between measures of realized and intrinsic predictability in both generated and real-world time series data (with the correlation coefficient being statistically significant at a 5% significance level). The discovered correlation in this research holds significant value for tasks related to evaluating time series complexity and their potential to be accurately predicted.https://www.mdpi.com/1099-4300/25/11/1542predictability measurestime series analysisintrinsic predictabilityrealized predictability |
| spellingShingle | Alexandra Bezbochina Elizaveta Stavinova Anton Kovantsev Petr Chunaev Enhancing Predictability Assessment: An Overview and Analysis of Predictability Measures for Time Series and Network Links Entropy predictability measures time series analysis intrinsic predictability realized predictability |
| title | Enhancing Predictability Assessment: An Overview and Analysis of Predictability Measures for Time Series and Network Links |
| title_full | Enhancing Predictability Assessment: An Overview and Analysis of Predictability Measures for Time Series and Network Links |
| title_fullStr | Enhancing Predictability Assessment: An Overview and Analysis of Predictability Measures for Time Series and Network Links |
| title_full_unstemmed | Enhancing Predictability Assessment: An Overview and Analysis of Predictability Measures for Time Series and Network Links |
| title_short | Enhancing Predictability Assessment: An Overview and Analysis of Predictability Measures for Time Series and Network Links |
| title_sort | enhancing predictability assessment an overview and analysis of predictability measures for time series and network links |
| topic | predictability measures time series analysis intrinsic predictability realized predictability |
| url | https://www.mdpi.com/1099-4300/25/11/1542 |
| work_keys_str_mv | AT alexandrabezbochina enhancingpredictabilityassessmentanoverviewandanalysisofpredictabilitymeasuresfortimeseriesandnetworklinks AT elizavetastavinova enhancingpredictabilityassessmentanoverviewandanalysisofpredictabilitymeasuresfortimeseriesandnetworklinks AT antonkovantsev enhancingpredictabilityassessmentanoverviewandanalysisofpredictabilitymeasuresfortimeseriesandnetworklinks AT petrchunaev enhancingpredictabilityassessmentanoverviewandanalysisofpredictabilitymeasuresfortimeseriesandnetworklinks |