HN Explorer

16 comments

[ 128 ms ] story [ 468 ms ] thread
jancsika
How about this-- give me a sticky toggle to switch to a dumb sorted list-- other channel content, alphabetical etc.

That at least lets the user run the experiment on themselves to check if the recommendation algo makes them sad.

The fact that the sentence above is based on a real thing Facebook did to its unwitting users speaks volumes about our shitty timeline.

dmarchand90
"Running a logistic regression might be too informed a baseline and can become a long drawn process."

What does this mean? To me it implies logistic regression is already so good that its hard to see the difference between it and most recommender systems. In which case, unless you're operating at massive scale, you can just go with logistic regression

Arkid
Logistic regression is a really good method and takes time to get right. But it is indeed one of the most performant models in multiple companies
Irishsteve
Depending on the size of the company (Revenue), and where / how the recommender system sits within the customer experience; Logistic regression could be fine. An even better baseline if discovery isn't so important for a good CX is to go with most popular and or a vendor. Building these systems used to be about getting lots of different things to work together which eats up a lot of time, and capacity (Product, UX, Eng) and it may not get the appropriate return.
rmbyrro
Please correct the title. It's "advice", not "advises".

Advise is a verb. It reads as if an organization called "Practical" is advising on something.

Edit: advice, no need for plural as in advices

Arkid
Made the change in the post. Thanks for this. Not able to change it here.
blenderdt
Most recommendations use the assumption that the user's need is the same at every point in time. This is why it doesn't work most of the time.

I think it's strange recommendation systems don't ask more about the context.

The answer to 'How do you feel today' can result in a total different playlist.

Or a python programmer who also likes snakes might want to set the context before a search (in DDG you can).

tpoacher
Based on the advices and the feedbacks received about our datas and evidences, we added syntactic sugars to our codes, which is sure to make us more moneys. Thank you for your hard works.

This is indeed excellent new.