Explainable Multivariate Time Series Classification: A Deep Neural Network Which Learns To Attend To Important Variables As Well As Time Intervals

Time series data is prevalent in a wide variety of real-world ap-plications and it calls for trustworthy and explainable models for people to understand and fully trust decisions made by AI solu-tions. We consider the problem of building explainable classifiers from multi-variate time series data. A key criterion to understand such predictive models involves elucidating and quantifying the contribution of time varying input variables to the classification. Existing approaches to explaining multi-variate time series classifiers aim to identify the key variables, and their values at specific time points which impact the classifier output. However, dynamics of time series data evolve with the progression of time and can only be comprehensively captured while taking into account consecutive observations within a time interval as opposed to considering only discrete time points. Hence, we introduce a novel,modular, convolution-based feature extraction and attention mechanism that simultaneously identifies the variables as well as time intervals which determine the classifier output. We present results of extensive experiments with several benchmark data sets that the proposed method outperforms the state-of-the-art baseline methods on multi-variate time series classification task. The results of our case studies demonstrate that the variables and time intervals identified by the proposed method make sense relative to available domain knowledge.