Attention models show promise in asset pricing research

A new research paper explores the application of advanced attention mechanisms, typically used in natural language processing, to the field of empirical asset pricing. The study specifically examines pre-trained Recurrent Neural Network (RNN) models with global and sparse attention variants on a large dataset of US stocks across different market conditions, including the COVID-19 pandemic. Findings indicate that these attention models can effectively derive returns and hedge risks, with global self-attention and sliding window sparse attention models showing strong performance, particularly during volatile periods. AI

IMPACT Advanced attention mechanisms from NLP show potential for improving financial modeling and risk management in empirical asset pricing.

RANK_REASON This is an academic paper published on arXiv detailing empirical research findings. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• RNN
• Shanyan Lai
• Transformer

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →