MlFinlab is a python package which helps portfolio managers and traders who want to leverage the power of machine learning by providing reproducible, interpretable, and easy to use tools. Adding MlFinLab to your companies pipeline is like adding a department of PhD researchers to your team.
pip install mlfinlab
We source all of our implementations from the most elite and peer-reviewed journals. Including publications from:
- The Journal of Financial Data Science
- The Journal of Portfolio Management
- The Journal of Algorithmic Finance
- Cambridge University Press
We are making a big drive to include techniques from various authors, however the most dominant author would be Dr. Marcos Lopez de Prado (QuantResearch.org). This package has its foundations in the two graduate level textbooks:
Praise for MlFinLab
“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 Prado, Co-founder and CIO at True Positive Technologies; Professor of Practice at Cornell University
"Those who doubt open source libraries just need to look at the impact of Pandas, Scikit-learn, and the like. MIFinLab is doing to financial machine learning what Tensorflow and PyTorch are doing to deep learning."
Dr. Ernest Chan, Hedge Fund Manager at QTS & Author
"For many decades, finance has relied on overly simplistic statistical techniques to identify patterns in data. Machine learning promises to change that by allowing researchers to use modern nonlinear and highly dimensional techniques. Yet, applying those machine learning algorithms to model financial problems is easier said than done: finance is not a plug-and-play subject as it relates to machine learning.
MlFinLab provides access to the latest cutting edges methods. MlFinLab is thus essential for quants who want to be ahead of the technology rather than being replaced by it."
Dr. Thomas Raffinot, Financial Data Scientist at ENGIE Global Markets
Unlocking the Commons
We are currently running a sponsorship model of “Unlocking the Commmons”. Our code base, online documentation, tutorial notebooks and presentations will remain open to everyone for so long as we can meet our minimum sponsorship goals. We have set the deadline: December 2020 - for a monthly total patronage of $4000 USD.
Nadia Eghbal explains it well: “If you'd like to open source a project but want to ensure that others will invest in its long-term maintenance, you could tell your community that you'll open-source the project once you've hit a certain amount of sponsorship. (Writer Tim Carmody refers to this as "unlocking the commons.")”
Documentation & Tutorials
Who is Hudson & Thames?
We are a private research group focused on implementing research based financial machine learning. We all work in virtual teams, spread across the world, primarily: New York, London, and Kyiv.
Sponsors and Donating
A special thank you to our sponsors! If you would like to become a sponsor and help support our research, please sign up on Patreon.
- Uninterrupted access: Should the code base pivot to closed source - your company will have access to all implementations and the source code.
- Ongoing access to slide show presentations and Jupyter Notebooks. (files can be edited to suit your personal needs such as classroom notes or client presentations.)
- Company / Organisation profile on www.hudsonthames.org
- Use of Hudson & Thames sponsor badge on your website.
- Access to our communities Slack Channel.
- Subscription to project release updates and news.
We host a booming community of like minded data scientists and quants, join the Slack Channel now! Open to sponsors of our package.
The channel has the following benefits:
- Community of like minded individuals.
- Ask questions about the package implementations and get community feedback.
- Occasional presentations on topics within financial machine learning.
- A papers channel where we share the papers which are freely available.
- Access to members of our research group.
Looking forward to hearing from you!
This project is licensed under an all rights reserved licence.
LICENSE.txt file for details.