# hudson-and-thames/mlfinlab

MlFinLab helps portfolio managers and traders who want to leverage the power of machine learning by providing reproducible, interpretable, and easy to use tools.

Repository: https://github.com/hudson-and-thames/mlfinlab
Canonical: https://ross.abutalabs.com/products/mlfinlab
Language: Python
License: NOASSERTION
License Family: other
Topics: machine-learning, trading, investing, research, finance, python, algorithmic-trading, quantitative-finance, financial-machine-learning, portfolio-management, portfolio-optimization
Last push: 2023-10-02T03:05:19+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2758, "days_push": 1066, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4913, forks 1285 (observed 2026-08-28T04:09:02.335798+00:00)

## What it is
MlFinLab is a Python library implementing financial machine learning techniques from data structure generation through labeling, feature engineering, cross-validation, and backtest statistics. It is a commercial, all-rights-reserved product by Hudson & Thames aimed at portfolio managers and quant researchers.

## Use cases
- implement financial machine learning strategies in python
- avoid backtest overfitting in trading strategies
- generate meta-labels and bet sizing for trades
- build features from tick data like bars and triple barrier labeling
- cross-validate financial time series without leakage
- estimate feature importance for trading models
- optimize a portfolio with machine learning techniques

## When to choose
- you need reproducible implementations of Lopez de Prado-style financial ML methods
- you are a quant team wanting tested, documented financial ML building blocks
- you want lecture videos and example notebooks alongside the code

## When to avoid
- you need a fully open-source library - it is all rights reserved and requires a paid license
- you want general-purpose machine learning rather than finance-specific tools
- you need actively maintained code - the public repo mainly serves issue tracking and releases have slowed

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, data-science, trading, data-generation, analytics
- domain: fintech, machine-learning, data-science
- platform: python
- tags: quantitative-finance, algorithmic-trading, financial-machine-learning, backtesting, portfolio-optimization, feature-engineering, cross-validation, bet-sizing, labeling, commercial-license

## Member repositories
- hudson-and-thames/mlfinlab (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:02.335798+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:18:03.981291+00:00, confidence not recorded.
  - readme: https://github.com/hudson-and-thames/mlfinlab (fetched 2026-08-28T04:09:02.335798+00:00, sha b1b9750d0d8a)
- Data as of 2026-08-30T08:39:29.467469+00:00.