A Performance-Explainability Framework to Benchmark Machine Learning Methods: Application to Multivariate Time Series Classifiers
This work addresses the need for standardized evaluation of explainability in machine learning, particularly for multivariate time series classification, but appears incremental as it systematizes existing assessments rather than introducing a novel method.
The authors proposed a new performance-explainability framework to assess and benchmark machine learning methods, applying it to evaluate state-of-the-art multivariate time series classifiers.
Our research aims to propose a new performance-explainability analytical framework to assess and benchmark machine learning methods. The framework details a set of characteristics that systematize the performance-explainability assessment of existing machine learning methods. In order to illustrate the use of the framework, we apply it to benchmark the current state-of-the-art multivariate time series classifiers.