Home / Risk & portfolio
universal-portfolios
Python collection of online portfolio selection algorithms
What it is
A Python collection of algorithms for online portfolio selection, the family of methods that rebalance a portfolio step by step as new prices arrive. Many classic strategies are implemented behind a common interface, which makes it easy to run them side by side and compare results. Researchers and students studying online portfolio optimisation can use it as an experiment bench. These are academic algorithms, and backtest results ignore many real-world frictions unless you model them yourself.
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, Backtesting |
| Markets | Multi-market |
| Stack | Python |
| Learning curve | Moderate learning curve |
| Practical value | Medium practical value |
| Cost | Free and open source |
| Hardware | No GPU needed |
| Maintenance | Last commit 5 days ago |
GitHub stars, last 30 days
Daily snapshots since 2026-09-28 (up to 30 days): +6 over the period, now 869. Gaps mean no snapshot was taken that day.
Collection of algorithms for online portfolio selection.
Similar tools
Vectorized pandas backtester and trading engine for QuantRocket
Machine learning framework for trading systems and market analysis
Vectorized Python backtesting and strategy research toolkit
Deep reinforcement learning library for automated quantitative trading
Python algorithmic trading framework with machine learning support
GPU-accelerated factor analysis and backtesting in Python