PyBroker

What it is

A Python framework for developing algorithmic trading strategies, with a focus on strategies that use machine learning. It offers a fast backtesting engine built on NumPy and Numba, walkforward analysis for model training, parameter optimization with Optuna, bootstrap-based evaluation metrics, and historical data from Alpaca, Yahoo Finance, AKShare, or custom providers. The framework suits quants and developers who want to write rules-based or model-based strategies across multiple instruments and time intervals in Python. Full use of its data integrations may require accounts with those providers, and the machine learning focus means users need some familiarity with building and training models.