Is attention truly all we need? An empirical study of asset pricing in pretrained RNN sparse and global attention models

TL;DR

This paper empirically evaluates pretrained RNN attention models with various attention mechanisms for asset pricing on large-cap US stocks, demonstrating their ability to better capture temporal dependencies and market dynamics, especially during extreme conditions.

Contribution

First large-scale application of state-of-the-art attention mechanisms in asset pricing, addressing limitations of traditional models and providing insights for future economic research.

Findings

Self-att and Sparse-att models excel in absolute returns and downside risk hedging.

Sparse-att model shows more stable performance across different stock sizes.

Models perform well during COVID-19 market extremes, with high Sortino ratios.

Abstract

This study investigates the pretrained RNN attention models with the mainstream attention mechanisms such as additive attention, Luong's three attentions, global self-attention (Self-att) and sliding window sparse attention (Sparse-att) for the empirical asset pricing research on top 420 large-cap US stocks. This is the first paper on the large-scale state-of-the-art (SOTA) attention mechanisms applied in the asset pricing context. They overcome the limitations of the traditional machine learning (ML) based asset pricing, such as mis-capturing the temporal dependency and short memory. Moreover, the enforced causal masks in the attention mechanisms address the future data leaking issue ignored by the more advanced attention-based models, such as the classic Transformer. The proposed attention models also consider the temporal sparsity characteristic of asset pricing data and mitigate potential overfitting issues by deploying the simplified model structures. This provides some insights for future empirical economic research. All models are examined in three periods, which cover pre-COVID-19 (mild uptrend), COVID-19 (steep uptrend with a large drawdown) and one year post-COVID-19 (sideways movement with high fluctuations), for testing the stability of these models under extreme market conditions. The study finds that in value-weighted portfolio back testing, Model Self-att and Model Sparse-att exhibit great capabilities in deriving the absolute returns and hedging downside risks, while they achieve an annualized Sortino ratio of 2.0 and 1.80 respectively in the period with COVID-19. And Model Sparse-att performs more stably than Model Self-att from the perspective of absolute portfolio returns with respect to the size of stocks' market capitalization.