Home / Factor research
Autoencoder-Asset-Pricing-Models
Reimplementation of autoencoder asset pricing models
What it is
A reimplementation of the autoencoder asset pricing models proposed by Gu, Kelly and Xiu. An autoencoder extracts latent pricing factors from a large set of characteristics to explain asset returns. Quant researchers, finance academics and developers interested in machine learning for asset pricing can study and reproduce the approach. It is a research reimplementation, so it needs the appropriate data and careful setup to match the paper's results.
At a glance
Research onlyOur rating, based on popularity, maintenance and how ready it is for real use.
| Best for | Professional quants |
|---|---|
| Used for | Strategy research, Data analysis |
| Markets | US equities, Multi-market |
| Stack | Python |
| Learning curve | Steep learning curve |
| Practical value | Medium practical value |
| Cost | Free and open source |
| Hardware | GPU optional |
| Maintenance | No commits in over six months |
GitHub stars, last 30 days
Daily snapshots since 2026-09-28 (up to 30 days): +1 over the period, now 154. Gaps mean no snapshot was taken that day.
Reimplementation of Autoencoder Asset Pricing Models ([GKX, 2019](https://www.aqr.com/Insights/Research/Working-Paper/Autoencoder-Asset-Pricing-Models)).
Similar tools
Transparent Python toolkit of financial metrics and ratios
Performance analysis of predictive stock factors
Pricing and Monte Carlo for stochastic volatility models
Jupyter notebooks companion to Machine Learning for Trading
Portfolio analytics and performance tear sheets for quants
scikit-learn compatible Python library for portfolio optimization