Generating Financial Time Series by Matching Random Convolutional Features

Published
Source
arXiv
Paper number
318
Field
Machine Learning
arXiv ID
2606.05138

Key points

  • To mitigate this, recent approaches train generators to minimize the mismatch between non-learned feature representations of real and generated time series.
  • This paper shows that a generator trained by matching random SOCK features consistently outperforms signature-based and diffusion-based baselines across multiple small-sample financial datasets.
  • The authors further demonstrate SOCK's expressiveness on two-sample hypothesis testing and time-series classification tasks, where SOCK matches or surpasses existing unsupervised feature maps.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)