UNLOCK CAPABILITY

pip install mlfinlab

MlFinLab is a collection of production-ready algorithms (from the best journals and graduate-level textbooks), packed into a python library that enables portfolio managers and traders who want to leverage the power of machine learning by providing reproducible, interpretable, and easy to use tools.

PURCHASE

SPEND LESS TIME BUILDING, USE IT

MlFinLab is built for teams who drive innovation.

PRODUCTION-READY

IMPLEMENTATIONS

DOCUMENTATION

EXAMPLE

NOTEBOOKS

RUNS LOCALLY

TIERS

2

Suiting your needs

MODULES

9+

Encompassing the latest research

PERSON HOURS

12672

In research and development

COVERAGE

100%

Production-ready code

MlFinlab Version 1.7.1

Financial Data Structures

When analyzing financial data, unstructured data sets are commonly transformed into a structured format referred to as bars, where a bar represents a row in a table. MlFinLab implements tick, volume, and dollar bars using traditional standard bar methods as well as the less common information driven bars.

Labelling Techniques

This module features a very comprehensive set of labeling techniques such as Triple-Barrier, Meta-Labeling, Trend Scanning, Tail Sets, and Matrix Flags.

Feature Engineriing

Feature engineering is the process of using domain knowledge to transform data into features for a model which are informative. We include famous techniques derived from market-microstructure, structural breaks, filters, and fractionally differentiated features.

Machine Learning

This module focuses on important modeling techniques needed for financial data science. Including feature importance, cross-validation, position-sizing, sampling, and sequentially bootstrapped ensembles.

Codependance and Networks

This module includes a comprehensive collection of codependence metrics, which can be used in portfolio construction, risk management, pairs trading, and informative features to a machine learning model.

Synthetic Data Generation

This module includes implementations of synthetic data generation algorithms as they relate to correlation matrices and financial time series. We include the well-known CORGAN model as well as all the landmark papers such as vine, extended onion, and HCBM.

Backtest Overfitting

Backtests are well known to overfit and promote false investment discoveries. The module provides award-winning frameworks – which minimize the chances of a false discovery. It includes algorithms such as the deflated and hair cut sharpe ratios, profit hurdles, minimum track record length, and more.

Clustering Techniques

Finance has its own set of clustering algorithms such as the Optimal Number of Clusters (ONC) algorithm which can be used to filter out false investment strategies, cluster similar assets for portfolio optimisation, and help select important features for modeling.

Networks Modelling

The Networks module creates beautiful and informative visualizations of financial data, using network theory to describe complex systems such as financial markets. In addition to this, portfolios can be constructed which outperform during market crashes, such as the COVID19 pandemic. Long short portfolios with their own unique alpha, may also be leveraged.

“Financial markets are complex systems like no other. Extracting signal from financial data requires specialized tools that are distinct from those used in general machine learning. The MlFinLab package compiles important algorithms that every quant should know and use.”

DR. MARCOS LOPEZ DE PRADOGlobal Head - Quantitative Research & Development at ABU DHABI INVESTMENT AUTHORITY (ADIA); Professor of Practice at Cornell University

“MIFinLab is doing to financial machine learning what Tensorflow and PyTorch are doing to deep learning.”

DR. ERNEST CHANHedge Fund Manager at QTS & Author

“MlFinLab forms the basis of an open toolbox to study correlations, hierarchies, networks and clustering in financial markets.”

DR. GAUTIER MARTI Abu Dhabi Investment Authority (ADIA) Quantitative Researcher & Developer; Founder of Abu Dhabi Machine Learning; Founder of Hong Kong Machine Learning

“Financial markets are complex systems like no other. Extracting signal from financial data requires specialized tools that are distinct from those used in general machine learning. The MlFinLab package compiles important algorithms that every quant should know and use.”

DR. MARCOS LOPEZ DE PRADOGlobal Head - Quantitative Research & Development at ABU DHABI INVESTMENT AUTHORITY (ADIA); Professor of Practice at Cornell University

“MIFinLab is doing to financial machine learning what Tensorflow and PyTorch are doing to deep learning.”⠀⠀⠀

DR. ERNEST CHANHedge Fund Manager at QTS & Author

“MlFinLab forms the basis of an open toolbox to study correlations, hierarchies, networks and clustering in financial markets.”

DR. GAUTIER MARTI Abu Dhabi Investment Authority (ADIA) Quantitative Researcher & Developer; Founder of Abu Dhabi Machine Learning; Founder of Hong Kong Machine Learning

CHOOSE YOUR TIER