Theoretically Motivated Data Augmentation and Regularization for Portfolio Construction

Code

• github.com/pfnet-research/finance_data_augmentation_icaif2022
  OfficialIn paperpytorch★ 3

Abstract

The task we consider is portfolio construction in a speculative market, a fundamental problem in modern finance. While various empirical works now exist to explore deep learning in finance, the theory side is almost non-existent. In this work, we focus on developing a theoretical framework for understanding the use of data augmentation for deep-learning-based approaches to quantitative finance. The proposed theory clarifies the role and necessity of data augmentation for finance; moreover, our theory implies that a simple algorithm of injecting a random noise of strength |r_t-1| to the observed return r_t is better than not injecting any noise and a few other financially irrelevant data augmentation techniques.

Tasks

Reproductions