MONSTER: Monash Scalable Time Series Evaluation Repository
This provides a new benchmark for researchers in time series classification, addressing the gap in large-scale data evaluation, though it is incremental as it builds on existing repositories like UCR and UEA.
The authors tackled the problem of limited dataset sizes in time series classification by introducing MONSTER, a repository of large datasets, to diversify the field and encourage models that address scalability and computational issues.
We introduce MONSTER-the MONash Scalable Time Series Evaluation Repository-a collection of large datasets for time series classification. The field of time series classification has benefitted from common benchmarks set by the UCR and UEA time series classification repositories. However, the datasets in these benchmarks are small, with median sizes of 217 and 255 examples, respectively. In consequence they favour a narrow subspace of models that are optimised to achieve low classification error on a wide variety of smaller datasets, that is, models that minimise variance, and give little weight to computational issues such as scalability. Our hope is to diversify the field by introducing benchmarks using larger datasets. We believe that there is enormous potential for new progress in the field by engaging with the theoretical and practical challenges of learning effectively from larger quantities of data.