Theoretically Motivated Data Augmentation and Regularization for Portfolio Construction

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 $\sqrt{|r_{t-1}|}$ to the observed return $r_t$ is better than not injecting any noise and a few other financially irrelevant data augmentation techniques.

The full version of our work published at 3rd ACM International Conference on AI in Finance (ICAIF'22)

References in corpus (2)

• Quant GANs: Deep Generation of Financial Time Series
• Deep Learning for Portfolio Optimization

Cited by in corpus (1)

• Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction