Related Posts
This bowl is dead!
Leaving 😬
How much in hand if 12 lpa package in TTL
Additional Posts in Data & Analytics Consultants
What is a data lake in basic terms?
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.
https://www.pnas.org/content/117/15/8398
New to Fishbowl?
unlock all discussions on Fishbowl.




Why would you use NLP to forecast demand? Sounds like you need to regression approach or a time series approach.
It's not for a case, but I like to play with NLP and thought using transformers as a backbone.
I have worked on ECG classification and tried this trick, but it was for a classification. I was thinking about doing the same for a time series forecast. Maybe it's not a good idea.
Bowl Leader
Seems reasonable to explore for fun, but otherwise I'd stay conventional. Gut says you won't have nearly enough data for transformers in most cases. But as always, depends... Quarterly B2B contracts volume isn't exactly the same as by the minute demand on data center resources.