INSHAPE

INSHAPE: Instance-Level Shapelets for Interpretable Time-Series Classification

INSHAPE is a new interpretable time-series classification framework that discovers variable-length discriminative temporal patterns specific to individual instances rather than across the full dataset population. It models temporal dependencies among non-overlapping segments and bridges local and global interpretability via a bottom-up aggregation into prototypical shapelets. Evaluated on 128 UCR and 30 UEA benchmark datasets, INSHAPE outperforms state-of-the-art shapelet-based methods while offering more intuitive instance-level explanations.