TSMix: time series data augmentation by mixing sources

Luke Darlow, Martin Asenov, Artjom Joosen, Qiwen Deng, Jianfeng Wang, Adam David Barker

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Data augmentation for time series is challenging because of the complex multi-scale relationships spanning ordered continuous sequences: one cannot easily alter a single datum and expect these relationships to be preserved. Time series datum are not independent and identically distributed random variables. However, modern Function as a Service (FaaS) infrastructure yields a unique opportunity for data augmentation because of the multiple distinct functions within a single data source. Further, common strong periodicity afforded by the human diurnal cycle and its link to these data sources enables mixing distinct functions to form pseudo-functions for improved model training. Herein we propose time series mix (TSMix), where pseudo univariate time series are created by mixing combinations of real univariate time series. We show that TSMix improves the performance on held-out test data for two state-of-the-art forecast models (N-BEATS and N-HiTS) and linear regression.

Original languageEnglish
Title of host publicationEuroMLSys '23
Subtitle of host publicationproceedings of the 3rd workshop on machine learning and systems
EditorsEiko Yoneki, Luigi Nardi
Place of PublicationNew York, NY
Number of pages6
ISBN (Print)9798400700842
Publication statusPublished - 6 May 2023


  • Datasets
  • Neural networks
  • Cloud infrastructure
  • Data augmentation


Dive into the research topics of 'TSMix: time series data augmentation by mixing sources'. Together they form a unique fingerprint.

Cite this