Hi! 👋

I'm Max, a data scientist who loves sharing and doing open-source. I like to play around with a lot of different, but most importantly I maintain River, which is a one of its kind Python library for doing online machine learning.

I have a somewhat unconventional view about doing machine learning models in production. An increasing amount of data sources are sequential in nature. Therefore, it makes sense to want to use models that are able to process streaming data. Alas, I personally believe that the existing open-source machine learning ecosystem isn't mature enough when it comes to machine learning on streaming data. There are still a lot challenges to figure out.

That's why I've been working on River since January 2019. Since then I've made a lot of progress, and I've managed to instigate a growing community around the project. We're proud to say that we're the most complete and fastest Python library out there when it comes to learning from a stream of single instances. We also put a lot of thought into API friendliness.

My current goal is to keep gathering momentum around the project, as well as working hand-in-hand with companies and practitioners. By funding me, you will give me more incentive and resources to add new features to River, whilst improving its quality and easy of use for everyone to enjoy.

Keep it real ✌️