Explainable Time Series Tweaking via Irreversible and Reversible Temporal Transformations

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.

Counterfactual Explanations for Multivariate Time Series

“…Wachter et al are among the first to use the term "counterfactual" for ML explanations [25]. Counterfactual explanations have also been used in the domains of image [26], document [27] and univariate time series [28] classification.…”

Locally and globally explainable time series tweaking

“…We define the problem of global explainable time series tweaking for the k-nearest neighbor classifier 2 and present a simple solution to tackle this problem. Eventually, we show that our algorithm for finding a transformation T for the k-nearest neighbor classifier is a generalization of the 1-nearest neighbor approach presented by Karlsson et al [21].…”

“…Note that for k = 1, the algorithm proposed here is equivalent to the baseline algorithm for the 1-nearest neighbor proposed by Karlsson et al [21]. The explanation to this is simply that for the case of 1-nearest neighbor, where, by definition, k = 1, we have that C = |X|.…”

“…An earlier version of the algorithm, restricted to k = 1, was presented together with a limited empirical evaluation in Karlsson et al[21].…”

“…Note that this is a generalization of the baseline method for 1-nearest neighbor presented in Karlsson et al[21].…”