Never a Dull Moment: Distributional Properties as a Baseline for Time-Series Classification

TMLR Paper9058 Authors

Abstract: The variety of complex algorithmic approaches for tackling time-series classification problems has grown considerably over the past decades, including the development of sophisticated but challenging-to-interpret deep-learning-based methods. But without comparison to simpler methods, it can be difficult to determine whether such complexity is required to obtain strong performance on a given problem. Here, we evaluate the performance of an extremely simple classification approach: a linear classifier in the space of two basic features that ignore the sequential ordering of the data: the mean and standard deviation of time-series values. Across a large repository of 129 (after filtering) univariate time-series classification problems, this simple distributional moment-based approach outperformed chance on 71 problems and reached 100% accuracy on two problems. In an additional neuroimaging time-series classification case study, we find that a simple linear model based on the mean and standard deviation performs better at classifying individuals with schizophrenia than a model that additionally includes features of the time-series dynamics, with performance sitting within the range of current literature. We conclude that comparing the performance of simple distributional features of a time series provides important context for interpreting the performance of more complex features or methods, which may not always be required to obtain high accuracy.

Submission Type: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Ali_Etemad1

Submission Number: 9058