Features were generated using normalization and other techniques - see using the Classification Learner app.
Given that people are not always good at assessing their own attractiveness, how does it affect the ultimate goal - getting matches?
Let's focus on average looking people (people who rate themselves 6 or 7) only to level the field and see how the self assessment affects the outcome.
This image is of a poster, and the copyright for it is most likely owned by either the publisher or the creator of the work depicted.
It is believed that the use of scaled-down, low-resolution images of posters qualifies as fair use under the copyright law of the United States.
What percentage of initial dates resulted in matches?
In order to make a match, you need to request another date and get that request accepted.
If they don't matter, it shouldn't increase the error rate much, right?
Based on those scores, the most important features are: scores indicate how much more attractive the partners were relative to the participants.
Any other uses of this image, on Wikipedia or elsewhere, may be copyright infringement.