triple_barrier
Unverified ML strategy on Multi by mchiuminatto. BotFinder score 18 out of 100.
Semi vectorized trades labeler for back-testing and machine learning pipelines
Source: github
BotFinder analysis pending.
triple_barrier
WARNING: This library has not been tested for real trading yet, test it first for your traind style and instruments and strategies. Overview Triple Barrier is a trade labeler that can be used for algorithmic trading back-testing or machine learning training and validating pipelines. It records for each trade when, at what price level and why a position was closed. It includes features to plot the triple for a particular trade and the closing event: Other features: - Built upon pandas, numpy, matplotlib mplfinance. - It can be used to label single trades or semi vectorized, meaning that can be used with a pandas apply function. Why? This project emerges from a repeated trading strategy back-testing process where I was caught again and again copying and pasting from previous pipelines the code to perform a vectorized (semi-vectorized to be more accurate) labeling of trades. To avoid this DRY (Do not Repeat Yourself) routine, that is why I decided to move this code to a library. Before moving further into the library details a little bit of context. Trading Strategies A trading strategy
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
Data unavailable — contact the owner.
Verification ledger
How the score has moved
Recalculated at each data collection. Transparency means showing the bad weeks too.
No score history is stored yet — only the current score is shown.
Reviews & comments
No reviews collected from the source yet.
⚠ No live verification account connected — ask for proof before buying.
Alerts on changes: coming soon
Prop-firm compatibility not provided.
Open-source maintainer on GitHub.
Data-completeness & trust index (not a profitability rating)