This is madness. 60% accuracy at best on your training dataset (2019 data)! So it will be in all likelihood worse on the 2020 data. How did anyone approve this to be used. And it's not like it's important to a whole heap of people's future. Awful.

from Twitter


Popular posts from this blog

A census of amplified and overexpressed human cancer genes : Nature Reviews Cancer

RT @CancerInNorwich: 📢 Join us on Monday at 1pm for the next talk in our virtual seminar series. We will be hearing from Dr Wafa Al-Jamal from @QUBelfast, who will be talking about "Smart Nanomedicimes for Pancreatic Cancer". All are welcome to join via the MS Teams link:

Universal Scrobbler