Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

What is a good way to do "triple barrier" and "trend scanning" with Backtesting and Scikit-Learn? #1138

Unanswered
BradKML asked this question in Q&A
Discussion options

Just saw that this is being used to create classification data for making strategy.
would like to see the "triple barrier" to be used to tag different times (early stop loss vs horizontal moves vs high potential to win) https://www.mlfinlab.com/en/latest/labeling/tb_meta_labeling.html
Similarly "trend scanning" would be good for finding ways to enter and exit in the most minimal way https://www.mlfinlab.com/en/latest/labeling/labeling_trend_scanning.html

You must be logged in to vote

Replies: 1 comment

Comment options

Noted that others have made an "extension" of the idea https://github.com/nkonts/barrier-method
See also this notebook https://github.com/maxzager/Financial-series-and-Triple-Barrier-Method

You must be logged in to vote
0 replies
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
1 participant

AltStyle によって変換されたページ (->オリジナル) /