# Deep Learning in Asset Pricing

## TL;DR

This paper introduces a deep learning-based asset pricing model that leverages extensive macroeconomic data and a no-arbitrage criterion, outperforming traditional models in predictive accuracy and economic interpretation.

## Contribution

It develops a novel deep neural network framework for asset pricing that incorporates macroeconomic states and a no-arbitrage condition, providing superior out-of-sample performance.

## Key findings

- Outperforms benchmarks in Sharpe ratio, explained variation, and pricing errors.
- Identifies key macroeconomic factors influencing asset prices.
- Uses adversarial approach to construct informative test assets.

## Abstract

We use deep neural networks to estimate an asset pricing model for individual stock returns that takes advantage of the vast amount of conditioning information, while keeping a fully flexible form and accounting for time-variation. The key innovations are to use the fundamental no-arbitrage condition as criterion function, to construct the most informative test assets with an adversarial approach and to extract the states of the economy from many macroeconomic time series. Our asset pricing model outperforms out-of-sample all benchmark approaches in terms of Sharpe ratio, explained variation and pricing errors and identifies the key factors that drive asset prices.