# Scalable Dictionary Classifiers for Time Series Classification

## TL;DR

This paper introduces RBOSS, a scalable, randomized ensemble method for time series classification that reduces build time significantly while maintaining accuracy, enabling application to larger datasets.

## Contribution

The paper proposes RBOSS, a scalable, randomized ensemble approach for dictionary-based TSC, replacing parameter search with random selection and ensembling techniques.

## Key findings

- RBOSS reduces build time substantially compared to BOSS.
- RBOSS maintains comparable accuracy to BOSS on standard datasets.
- RBOSS enables application to large datasets like whale acoustics.

## Abstract

Dictionary based classifiers are a family of algorithms for time series classification (TSC), that focus on capturing the frequency of pattern occurrences in a time series. The ensemble based Bag of Symbolic Fourier Approximation Symbols (BOSS) was found to be a top performing TSC algorithm in a recent evaluation, as well as the best performing dictionary based classifier. A recent addition to the category, the Word Extraction for Time Series Classification (WEASEL), claims an improvement on this performance. Both of these algorithms however have non-trivial scalability issues, taking a considerable amount of build time and space on larger datasets. We evaluate changes to the way BOSS chooses classifiers for its ensemble, replacing its parameter search with random selection. This change allows for the easy implementation of contracting, setting a build time limit for the classifier and check-pointing, saving progress during the classifiers build. To differentiate between the two BOSS ensemble methods we refer to our randomised version as RBOSS. Additionally we test the application of common ensembling techniques to help retain accuracy from the loss of the BOSS parameter search. We achieve a significant reduction in build time without a significant change in accuracy on average when compared to BOSS by creating a size $n$ weighted ensemble selecting the best performers from $k$ randomly chosen parameter sets. Our experiments are conducted on datasets from the recently expanded UCR time series archive. We demonstrate the usability improvements to RBOSS with a case study using a large whale acoustics dataset for which BOSS proved infeasible.