Thought this was interesting. Across 160 teams of researchers, just about all failed to make good life outcome predictions on things like GPA, evictions, layoffs, and others. Data followed 4.5k families across 15 years, with 13k features (varied over time). Haven't looked at it directly yet, but will be turning the docs and data inside out... In the meantime, authors claim this as showing the limits of ML. Oh, and it's published in PNAS, so you know there's some big publication energy there.
Related Posts
Can I join in Nokia R&D unit for java, spring boot backend developer role considering current situation of layoffs in product based companies ?
Exp - 4 years
Tech stack - Java, Spring Boot, Microservices
EPAM Systems Cisco Nokia Dell Deloitte Deloitte USI Deloitte India Infosys Cognizant KPMG EY PwC Verizon Verizon Media Ericsson Huawei Technologies
More Posts
Who is at the Q center bored right now???
Additional Posts in Data & Analytics Consultants
New to Fishbowl?
unlock all discussions on Fishbowl.







Is the ML getting stuck on local maximums? You would think with that many features you could curve fit something with the phases of the moon.
Mentor
It’s a good cautionary point, not everything is as black and white as making a spam filter.