Proximity Forest

an effective and scalable distance-based classifier for time series

Benjamin Lucas, Ahmed Shifaz, Charlotte Pelletier, Lachlan O’Neill, Nayyar Zaidi, Bart Goethals, François Petitjean, Geoffrey I. Webb

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Research into the classification of time series has made enormous progress in the last decade. The UCR time series archive has played a significant role in challenging and guiding the development of new learners for time series classification. The largest dataset in the UCR archive holds 10,000 time series only; which may explain why the primary research focus has been on creating algorithms that have high accuracy on relatively small datasets. This paper introduces Proximity Forest, an algorithm that learns accurate models from datasets with millions of time series, and classifies a time series in milliseconds. The models are ensembles of highly randomized Proximity Trees. Whereas conventional decision trees branch on attribute values (and usually perform poorly on time series), Proximity Trees branch on the proximity of time series to one exemplar time series or another; allowing us to leverage the decades of work into developing relevant measures for time series. Proximity Forest gains both efficiency and accuracy by stochastic selection of both exemplars and similarity measures. Our work is motivated by recent time series applications that provide orders of magnitude more time series than the UCR benchmarks. Our experiments demonstrate that Proximity Forest is highly competitive on the UCR archive: it ranks among the most accurate classifiers while being significantly faster. We demonstrate on a 1M time series Earth observation dataset that Proximity Forest retains this accuracy on datasets that are many orders of magnitude greater than those in the UCR repository, while learning its models at least 100,000 times faster than current state-of-the-art models Elastic Ensemble and COTE.

Original languageEnglish
Pages (from-to)607-635
Number of pages29
JournalData Mining and Knowledge Discovery
Volume33
Issue number3
DOIs
Publication statusPublished - May 2019

Keywords

  • Ensemble
  • Scalable classification
  • Time series classification
  • Time-warp similarity measures

Cite this

Lucas, Benjamin ; Shifaz, Ahmed ; Pelletier, Charlotte ; O’Neill, Lachlan ; Zaidi, Nayyar ; Goethals, Bart ; Petitjean, François ; Webb, Geoffrey I. / Proximity Forest : an effective and scalable distance-based classifier for time series. In: Data Mining and Knowledge Discovery. 2019 ; Vol. 33, No. 3. pp. 607-635.
@article{41e720ca83684d4ab190c06409797886,
title = "Proximity Forest: an effective and scalable distance-based classifier for time series",
abstract = "Research into the classification of time series has made enormous progress in the last decade. The UCR time series archive has played a significant role in challenging and guiding the development of new learners for time series classification. The largest dataset in the UCR archive holds 10,000 time series only; which may explain why the primary research focus has been on creating algorithms that have high accuracy on relatively small datasets. This paper introduces Proximity Forest, an algorithm that learns accurate models from datasets with millions of time series, and classifies a time series in milliseconds. The models are ensembles of highly randomized Proximity Trees. Whereas conventional decision trees branch on attribute values (and usually perform poorly on time series), Proximity Trees branch on the proximity of time series to one exemplar time series or another; allowing us to leverage the decades of work into developing relevant measures for time series. Proximity Forest gains both efficiency and accuracy by stochastic selection of both exemplars and similarity measures. Our work is motivated by recent time series applications that provide orders of magnitude more time series than the UCR benchmarks. Our experiments demonstrate that Proximity Forest is highly competitive on the UCR archive: it ranks among the most accurate classifiers while being significantly faster. We demonstrate on a 1M time series Earth observation dataset that Proximity Forest retains this accuracy on datasets that are many orders of magnitude greater than those in the UCR repository, while learning its models at least 100,000 times faster than current state-of-the-art models Elastic Ensemble and COTE.",
keywords = "Ensemble, Scalable classification, Time series classification, Time-warp similarity measures",
author = "Benjamin Lucas and Ahmed Shifaz and Charlotte Pelletier and Lachlan O’Neill and Nayyar Zaidi and Bart Goethals and Fran{\cc}ois Petitjean and Webb, {Geoffrey I.}",
year = "2019",
month = "5",
doi = "10.1007/s10618-019-00617-3",
language = "English",
volume = "33",
pages = "607--635",
journal = "Data Mining and Knowledge Discovery",
issn = "1384-5810",
publisher = "Springer",
number = "3",

}

Proximity Forest : an effective and scalable distance-based classifier for time series. / Lucas, Benjamin; Shifaz, Ahmed; Pelletier, Charlotte; O’Neill, Lachlan; Zaidi, Nayyar; Goethals, Bart; Petitjean, François; Webb, Geoffrey I.

In: Data Mining and Knowledge Discovery, Vol. 33, No. 3, 05.2019, p. 607-635.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Proximity Forest

T2 - an effective and scalable distance-based classifier for time series

AU - Lucas, Benjamin

AU - Shifaz, Ahmed

AU - Pelletier, Charlotte

AU - O’Neill, Lachlan

AU - Zaidi, Nayyar

AU - Goethals, Bart

AU - Petitjean, François

AU - Webb, Geoffrey I.

PY - 2019/5

Y1 - 2019/5

N2 - Research into the classification of time series has made enormous progress in the last decade. The UCR time series archive has played a significant role in challenging and guiding the development of new learners for time series classification. The largest dataset in the UCR archive holds 10,000 time series only; which may explain why the primary research focus has been on creating algorithms that have high accuracy on relatively small datasets. This paper introduces Proximity Forest, an algorithm that learns accurate models from datasets with millions of time series, and classifies a time series in milliseconds. The models are ensembles of highly randomized Proximity Trees. Whereas conventional decision trees branch on attribute values (and usually perform poorly on time series), Proximity Trees branch on the proximity of time series to one exemplar time series or another; allowing us to leverage the decades of work into developing relevant measures for time series. Proximity Forest gains both efficiency and accuracy by stochastic selection of both exemplars and similarity measures. Our work is motivated by recent time series applications that provide orders of magnitude more time series than the UCR benchmarks. Our experiments demonstrate that Proximity Forest is highly competitive on the UCR archive: it ranks among the most accurate classifiers while being significantly faster. We demonstrate on a 1M time series Earth observation dataset that Proximity Forest retains this accuracy on datasets that are many orders of magnitude greater than those in the UCR repository, while learning its models at least 100,000 times faster than current state-of-the-art models Elastic Ensemble and COTE.

AB - Research into the classification of time series has made enormous progress in the last decade. The UCR time series archive has played a significant role in challenging and guiding the development of new learners for time series classification. The largest dataset in the UCR archive holds 10,000 time series only; which may explain why the primary research focus has been on creating algorithms that have high accuracy on relatively small datasets. This paper introduces Proximity Forest, an algorithm that learns accurate models from datasets with millions of time series, and classifies a time series in milliseconds. The models are ensembles of highly randomized Proximity Trees. Whereas conventional decision trees branch on attribute values (and usually perform poorly on time series), Proximity Trees branch on the proximity of time series to one exemplar time series or another; allowing us to leverage the decades of work into developing relevant measures for time series. Proximity Forest gains both efficiency and accuracy by stochastic selection of both exemplars and similarity measures. Our work is motivated by recent time series applications that provide orders of magnitude more time series than the UCR benchmarks. Our experiments demonstrate that Proximity Forest is highly competitive on the UCR archive: it ranks among the most accurate classifiers while being significantly faster. We demonstrate on a 1M time series Earth observation dataset that Proximity Forest retains this accuracy on datasets that are many orders of magnitude greater than those in the UCR repository, while learning its models at least 100,000 times faster than current state-of-the-art models Elastic Ensemble and COTE.

KW - Ensemble

KW - Scalable classification

KW - Time series classification

KW - Time-warp similarity measures

UR - http://www.scopus.com/inward/record.url?scp=85061291606&partnerID=8YFLogxK

U2 - 10.1007/s10618-019-00617-3

DO - 10.1007/s10618-019-00617-3

M3 - Article

VL - 33

SP - 607

EP - 635

JO - Data Mining and Knowledge Discovery

JF - Data Mining and Knowledge Discovery

SN - 1384-5810

IS - 3

ER -