This looks really neat! Here's some unsolicited feedback:

> "Scientifically proven to measure you 20% more accurately than a professional tailor."

This probably isn't a priority for you guys, but it would be cool to see the data on this. You could easily make a white paper without releasing your actual ML process - how big is your sample set, were your control groups "blind" when they reported which shirt they like more, were the tailored shirts the same fabric, how did you pick your "average" tailor, etc.

The biggest reason on why I don't try a new clothing store is A) I don't know how well it'll fit me and B) returning things, even with prepaid slips, is still a hassle. For me, any little thing that convinces me I don't have to worry about returning goes a long way for trying a new store.