Augmenting transferred representations for stock classification

  • Elizabeth Fons1
    •
  • Paula Dawson2
    •
  • Xiao-jun Zeng1
    •
  • John Keane1
    •
  • Alexandros Iosifidis3
    •

     

     

    General training process with transfer learning and data augmentation. The panel on the left shows the pre-trained model and the new transferred one. On the centre, workflow of the two augmentation approaches, data augmentation on the feature space (top) and data augmentation on the input space (bottom); on the right, the resulting networks to be trained.

    Abstract

    Stock classification is a challenging task due to high levels of noise and volatility of stocks returns. In this paper we show that using transfer learning can help with this task, by pre-training a model to extract universal features on the full universe of stocks of the S&P500 index and then transferring it to another model to directly learn a trading rule. Transferred models present more than double the risk-adjusted returns than their counterparts trained from zero. In addition, we propose the use of data augmentation on the feature space defined as the output of a pre-trained model (\ie augmenting the aggregated time-series representation). We compare this augmentation approach with the standard one, i.e. augmenting the time-series in the input space. We show that augmentation methods on the feature space leads to 20% increase in risk-adjusted return compared to a model trained with transfer learning but without augmentation.

     

    Paper

     

    Bibtex

    Acknowledgement

    This work was supported by the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie Grant Agreement no. 675044 (http://bigdatafinance.eu/), Training for Big Data in Financial Research and Risk Management. A. Iosifidis acknowledges funding from the Independent Research Fund Denmark project DISPA (Project Number: 9041-00004).