TY - GEN
T1 - Explainable time series tweaking via irreversible and reversible temporal transformations
AU - Karlsson, Isak
AU - Rebane, Jonathan
AU - Papapetrou, Panagiotis
AU - Gionis, Aristides
N1 - | openaire: EC/H2020/654024/EU//SoBigData
PY - 2018
Y1 - 2018
N2 - 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.
AB - 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.
U2 - 10.1109/ICDM.2018.00036
DO - 10.1109/ICDM.2018.00036
M3 - Conference contribution
SN - 9781538691601
T3 - International Conference on Data Mining Proceedings
SP - 207
EP - 216
BT - 2018 IEEE International Conference on Data Mining, ICDM 2018
PB - IEEE
T2 - IEEE International Conference on Data Mining
Y2 - 17 November 2018 through 20 November 2018
ER -