Hacker News Reader

Comment by amilanez | Hacker News Reader

I don't imagine that crowd-sourcing would work well -- body types vary wildly withing a given size. A size 6 isn't a size 6 isn't a size 6 . . .

View on HN

I'm guessing the long term of the suggestions would be you would see that this dress fits similar to how a dress you own fits, thus implying that you could probably wear it.

1) Not every person wants the same kind of fit(snug,slim,skinny,relaxed,classic,natural, etc) or drape.

2) Look at this image to see the difference between different brands and their size 8 measurements.

http://www.nytimes.com/imagepages/2011/04/24/business/201104... via http://thesocietypages.org/graphicsociology/tag/womens-size-...

There's many variables to sizing. It wouldn't be impossible to create a database of measurements for every single piece of clothing.

And then there's the issue of shrinkage.

1) Not every person wants the same kind of fit(snug,slim,skinny,relaxed,classic,natural, etc) or drape.

Those are irrelevant details. The basic form of input is "person A gives rating R to item B". This is precisely the formulation behind successful solutions to the netflix problem.

You would need a pretty well-populated training set (assuming SVD or similar ML algorithm), I imagine, and somehow I think that might be difficult with so many unique item Bs. With Netflix you have many people watching the same movie, but I think there are many more dresses around, and women probably won't be rating hundreds/thousands of them (which is easier to do on movies).

The Yahoo Music dataset has these characteristics (more items than users), and a combination of methods (including the SGD-based matrix factorization that people call "SVD" in recommender lore) did pretty well on it (KDD Cup 2011: http://kddcup.yahoo.com/).

Interesting, thanks for the link.

What I find a little disappointing is that the top 3 prizes for this Netflix-Prize-style competition total $7,000 in value. Is technical brainpower, even that of students, really worth that little? Maybe startups should band together to hold their own optimization contests if the 'market rates' are so low.

Right. I'm not sure why others are misunderstanding how crowd-sourcing this information helps solves the problem.

People saying that size numbers vary greatly are missing the point. If I say a particular piece fits me well (regardless of its listed size) and then a bunch of other people say it fits them well (regardless of its listed size), the site can then aggregate the other pieces of clothing that those people said fit them well to show me clothes that potentially fit me well (regardless of their listed sizes).

Very true. However, once there is some data generated about how well the item fit the user, you can probably make some correlations and determine just what will fit who.

I would just call it data analysis, not crowd-sourcing

Reply on news.ycombinator.com