qis: performance analytics, portfolio backtesting, risk analysis, and factsheet reporting¶
qis - performance analytics, portfolio backtesting, risk analysis, and factsheet reporting in Python.
Quantitative Investment Strategies covers time-series and cross-sectional performance, drift-aware portfolio histories, ex-ante and ex-post risk, and reproducible reports.
Install with pip install qis, then follow the offline quickstart for a
deterministic portfolio backtest, performance table, and benchmark-relative result. Its single
source is
examples/getting_started/offline_quickstart.py:
the documentation includes that complete runnable file rather than maintaining another code copy.
It needs no network, data vendor, credentials, optional extra, or output directory.
Project resources¶
JOSS submission paper (under review; not accepted or published)
Focused guides
- Performance analytics and Sharpe conventions
- Software design
- Factsheets and reporting
- Tracking error and benchmark-relative risk
- Portfolio backtesting: targets, held units, and implementation
- Incomplete and mixed-frequency data
- Private-asset unsmoothing and de-levering
- FX hedging and market-data boundaries
- Choosing between qis, QuantStats, pyfolio-reloaded, and vectorbt
Conventions
- Sharpe Ratio Conventions: Arithmetic vs. Per-Annum (Compound) Returns
- Reporting-frequency convention
- Performance Statistics Are Frequency-Relative: A Reporting Convention for Internally Consistent Factsheets
- Factsheets & reporting
- Shared plotting arguments
- qis 5.9.2 — removed from the public API
- qis 5.0 — removed from the public namespace
Reference