[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![PeterLBrandt Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::247857712.png) Peter Brandt [@PeterLBrandt](/creator/twitter/PeterLBrandt) on x 803.6K followers
Created: 2025-07-13 21:06:23 UTC

The truth about back-testing as I understand from real quants at firms such as Renaissance, Goldman, etc
X. Backtesting a discretionary approach is impossible
X. An approach with even XX% discretionary filtering is discretionary
X. Purely systematic approaches not back tested against every possible in-sample and out-of-sample data are untrustworthy
X. Only forward testing with pre-entered orders producing hundreds of trades with outcomes subjected to rigorous metrics is reliable. Everything else is a lie


XXXXXXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1944503696726876434/c:line.svg)

[Post Link](https://x.com/PeterLBrandt/status/1944503696726876434)