# akfamily/akquant

AKQuant is a high-performance quantitative research and trading framework built on Rust and Python! 开源量化回测框架

Repository: https://github.com/akfamily/akquant
Canonical: https://ross.abutalabs.com/products/akquant
Homepage: https://akquant.akfamily.xyz/
Language: Python
License: MIT
License Family: permissive
Topics: quant, akshare, backtest, finance
Last push: 2026-08-26T03:20:32+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 15
- inputs: {"age_days": 215, "days_push": 7, "days_rel": 8, "gap_med": 0, "n_releases_24m": 120}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2095, forks 274 (observed 2026-08-28T04:06:13.202055+00:00)

## What it is
AKQuant is a high-performance quantitative research and backtesting framework with a Rust core engine and Python interface for strategy development. It provides event-driven backtesting, machine learning integration (walk-forward validation with PyTorch/Scikit-learn), a factor expression engine, and built-in risk management.

## Use cases
- backtest trading strategies on historical stock data
- run walk-forward validation for ML-based trading strategies
- compute Alpha101-style factor expressions with Polars
- optimize strategy parameters with parallel grid search
- backtest multi-asset portfolios with risk controls
- fetch A-share market data via akshare and run backtests
- generate benchmark comparison reports for strategies

## When to choose
- you need fast event-driven backtesting with a Rust-optimized engine
- you want to combine machine learning models with trading strategy backtests
- you work with Chinese A-share market data via akshare
- you need built-in technical indicators, factor computation, and parameter optimization in one framework

## When to avoid
- you need live trading execution against real brokers rather than backtesting
- you require a large community ecosystem like Zipline or Backtrader with extensive third-party examples
- you need asset classes or markets beyond what the framework's data integrations support

## Facets
- artifact type: framework
- maturity: active
- function: simulation, machine-learning, data-science, benchmarking, sdk
- domain: fintech, quantum-computing, machine-learning, data-science
- platform: python, rust, cross-platform, windows
- tags: quantitative-finance, backtesting, trading-strategies, event-driven, walk-forward-validation, factor-analysis, akshare, rust-core, technical-indicators, parameter-optimization, macos, linux

## Member repositories
- akfamily/akquant (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:13.202055+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:54:38.626785+00:00, confidence not recorded.
  - readme: https://github.com/akfamily/akquant (fetched 2026-08-28T04:06:13.202055+00:00, sha 70ce01545da9)
  - homepage: https://akquant.akfamily.xyz/ (fetched 2026-08-29T10:35:05.131867+00:00, sha 063d5139fc50)
  - site_page: https://akquant.akfamily.xyz/start/installation (fetched 2026-08-29T10:35:05.141196+00:00, sha 45e58735c51c)
  - site_page: https://akquant.akfamily.xyz/start/quickstart (fetched 2026-08-29T10:35:05.143204+00:00, sha c75aff76c8f5)
- Data as of 2026-08-30T08:39:29.467469+00:00.