Attribyt is an open-source tool for multi-touch marketing attribution. Upload your customer journey data (CSV or Excel) and compare four attribution models side by side — Last-Click, Linear, Time Decay, and an exact Markov-chain removal-effect model. Everything runs locally via Docker, so your data never leaves your machine. Built with FastAPI, React, and Polars.
Hey everyone! 👋
I created this project just for fun, don’t look for any deep meaning here — I just thought it was interesting, that’s all. Maybe someone else will find it interesting too, lol.
Most tools default to Last-Click, which overpays bottom-of-funnel channels and undervalues the ones that actually create demand. Attribyt runs four models side by side so you can see the difference on your own data — including a real Markov-chain removal-effect model.
It's fully open-source and runs locally via Docker — no cloud, no data leaving your machine. If you have any ideas on how it could be improved or what you’d like to see here, please write — I’d be interested to hear your thoughts.
https://github.com/eapte/attribyt