MLFinLab
Implementations of the methods in López de Prado's financial machine learning work — triple-barrier labelling, fractional differentiation, purged cross-validation.
What it is good at
Purged and embargoed cross-validation is the single most important defence against the leakage that makes most financial ML backtests worthless.
Scored against the five published criteria, identically for every entry, by the editors of this site. Scores are never sold and are not affected by any commercial relationship. Read the method.
What to watch
An implementation of a research programme, not a neutral toolkit. Understand the underlying methodology before trusting the outputs.
This section is not optional and is not negotiable. Every entry in the register carries one, whatever the commercial relationship.
Access it
No commercial relationship. MLFinLab is listed on editorial merit and has no input into this description or its scores.