Our take
- Activity
- 53
- Community
- 42
- Issues
- 48
- Pull requests
- 20
+164 stars in the last 30 days
- Slower to close issues than 82% of the projects we track
Project history
Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.
Stars
7,886Forks
1,301Change since Nov 17, 2026: +8 stars·+1 forks
Overview
QuantStats analyzes portfolio return series to help quants and portfolio managers assess performance and risk. Its metrics cover measures such as Sharpe ratio, volatility, and drawdown, while plots and reports make results easier to inspect and share.
It works with daily, weekly, or monthly returns rather than discrete trade records. This distinction matters when interpreting metrics such as win rate: they describe positive and negative return periods, not individual trades.
Key Features
- Calculate performance and risk metrics, including Sharpe ratio, volatility, maximum drawdown, and value at risk.
- Visualize returns, drawdowns, rolling statistics, and monthly returns.
- Generate metrics and plot reports, including HTML tear sheets.
- Extend pandas objects with QuantStats metrics and plotting methods.
- Run Monte Carlo simulations for probabilistic risk analysis.
- Compare return series with a benchmark.
Use Cases
- A quant can profile a systematic strategy's periodic returns and review its risk metrics.
- A portfolio manager can compare a portfolio with a benchmark and produce an HTML report for review.
- An analyst can visualize drawdowns, rolling volatility, and monthly return patterns when investigating performance.
- A strategy researcher can use Monte Carlo simulations to examine bust and goal probabilities based on return data.
Getting Started
Install with pip:
pip install quantstats
Import it with import quantstats as qs. See the README for usage details and requirements.
Considerations
- The library analyzes return periods, not individual trade entries and exits. Period-based win and loss metrics may therefore differ from trade-level statistics.
- The README lists Python 3.10 or newer and minimum versions for pandas, NumPy, SciPy, Matplotlib, Seaborn, tabulate, and yfinance. Plotly is optional for
plots.to_plotly(). - The README notes a plotting caveat: saving the monthly returns heatmap may still display it.
Found this useful?
Share it with someone who would like quantstats.