Explainable time series tweaking via irreversible and reversible temporal transformations

Isak Karlsson, Jonathan Rebane, Panagiotis Papapetrou, Aristides Gionis

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

16 Citations (Scopus)

Abstract

Time series classification has received great attention over the past decade with a wide range of methods focusing on predictive performance by exploiting various types of temporal features. Nonetheless, little emphasis has been placed on interpretability and explainability. In this paper, we formulate the novel problem of explainable time series tweaking, where, given a time series and an opaque classifier that provides a particular classification decision for the time series, we want to find the minimum number of changes to be performed to the given time series so that the classifier changes its decision to another class. We show that the problem is NP-hard, and focus on two instantiations of the problem, which we refer to as reversible and irreversible time series tweaking. The classifier under investigation is the random shapelet forest classifier. Moreover, we propose two algorithmic solutions for the two problems along with simple optimizations, as well as a baseline solution using the nearest neighbor classifier. An extensive experimental evaluation on a variety of real datasets demonstrates the usefulness and effectiveness of our problem formulation and solutions.
Original languageEnglish
Title of host publication2018 IEEE International Conference on Data Mining, ICDM 2018
PublisherIEEE
Pages207-216
Number of pages10
ISBN (Electronic)9781538691588
ISBN (Print)9781538691601
DOIs
Publication statusPublished - 2018
MoE publication typeA4 Article in a conference publication
EventIEEE International Conference on Data Mining - Singapore, Singapore
Duration: 17 Nov 201820 Nov 2018

Publication series

NameInternational Conference on Data Mining Proceedings
PublisherIEEE
ISSN (Print)1550-4786
ISSN (Electronic)2374-8486

Conference

ConferenceIEEE International Conference on Data Mining
Abbreviated titleICDM
Country/TerritorySingapore
CitySingapore
Period17/11/201820/11/2018

Fingerprint

Dive into the research topics of 'Explainable time series tweaking via irreversible and reversible temporal transformations'. Together they form a unique fingerprint.

Cite this