How Normal Am I?

#1

Post by innot » Wed, Sep 30, 2020, 9:57 AM UTC

How Normal Am I?
hownormalami.eu

Re: How Normal Am I?

#2

Post by chromatin » Wed, Sep 30, 2020, 6:44 PM UTC

Very interesting, but hangs at the last(?) step (life expectancy)

Re: How Normal Am I?

#3

Post by kevinmgranger » Wed, Sep 30, 2020, 6:49 PM UTC

I think the link to the Sherpa Project is wrong. It should be https://www.project-sherpa.eu/

Re: How Normal Am I?

#4

Post by nbulka » Wed, Sep 30, 2020, 6:58 PM UTC

chromatin wrote: post #2

Very interesting, but hangs at the last(?) step (life expectancy)

Could they be trying to make a point? About insurance abuses of this technology maybe? maybe not, could just be the algorithm failing. Or maybe they don't want to assume the liability of actually providing a number.

Re: How Normal Am I?

#5

Post by yosser » Wed, Sep 30, 2020, 7:05 PM UTC

nbulka wrote: post #4

chromatin wrote: post #2

Very interesting, but hangs at the last(?) step (life expectancy)

Could they be trying to make a point? About insurance abuses of this technology maybe? maybe not, could just be the algorithm failing. Or maybe they don't want to assume the liability of actually providing a number.

No, it's a javascript error. The second time around I agreed to the terms and conditions and then the site worked fine.

Re: How Normal Am I?

#6

Post by wodenokoto » Wed, Sep 30, 2020, 7:57 PM UTC

That was simply amazing. Having the video guide you through all the machine learning prediction steps as they got analyzed on your video feed worked flawless, both in terms of technical execution but also presentatio nwise.

They also made some great points about how ridiculous some of these algorithms are (shake your head to lose 10 years of age, or just trying to predict BMI from a face photo)

Re: How Normal Am I?

#7

Post by owouwuowo » Wed, Sep 30, 2020, 8:01 PM UTC

Apperantly when the website thinks you are a woman, it marks that column down as "Normal: No", because 82% of visitors are men.

Just something to think about.

Also it called me ugly :Edit:

I just ran the website for a second time and didn't change my clothes or anything, and it gave me very different results.

ie. gender, age, bmi, attractiveness all different.

I don't think the ratings for this is very stable & reproducible.

at least it rated my girlfriend as abnormally attractive. :)

Re: How Normal Am I?

#8

Post by socialcooling » Wed, Sep 30, 2020, 8:17 PM UTC

kevinmgranger wrote: post #3

I think the link to the Sherpa Project is wrong. It should be https://www.project-sherpa.eu/

You're right! Thanks, I've fixed it!

Re: How Normal Am I?

#9

Post by socialcooling » Wed, Sep 30, 2020, 8:18 PM UTC

yosser wrote: post #5

nbulka wrote: post #4

Earlier quoted context omitted.

Could they be trying to make a point? About insurance abuses of this technology maybe? maybe not, could just be the algorithm failing. Or maybe they don't want to assume the liability of actually providing a number.

No, it's a javascript error. The second time around I agreed to the terms and conditions and then the site worked fine.

Yikes. Thanks, I'll look into it. The terms and conditions have no influence on this, but it could that that one of the scores required to create the life expectancy prediction is missing (age, gender, bmi, country).

Re: How Normal Am I?

#10

Post by socialcooling » Wed, Sep 30, 2020, 8:21 PM UTC

owouwuowo wrote: post #7

Apperantly when the website thinks you are a woman, it marks that column down as "Normal: No", because 82% of visitors are men. Just something to think about. Also it called me ugly : Edit: I just ran the website for a second time and didn't change my clothes or anything, and it gave me very different results. ie. gender, age, bmi, attractiveness all different. I don't think the ratings for this is very stable & repr…

Age and gender are derived using the FaceApiJS project. In my own experience it's doesn't vary as wildly if you're a white male. With other ethnicities the predictability levels can drop, especially if you're Asian.