What does cognitive psychology tell us about how this new choice context affects our happiness? Massimo and Julia turn an analytical eye on the math and science of online dating, in this episode of Rationally Speaking.
Julia's pick: "Seeing Like a State: How Certain Schemes to Improve the Human Condition Have Failed"
Massimo's pick: "Do different kinds of alcohol get you different kinds of drunk?"
Sounds like their matching algorithms are still based on their intuitions and manual data analysis, in which case they should try discovering patterns with machine learning. The patterns might not be intuitive, but they work.
ReplyDeletehttp://www.slate.com/articles/health_and_science/new_scientist/2012/12/kaggle_president_jeremy_howard_amateurs_beat_specialists_in_data_prediction.html
"The messages are uncomfortable for a lot of people. It's controversial because we're telling them: Your decades of specialist knowledge are not only useless, they're actually unhelpful; your sophisticated techniques are worse than generic methods. It's difficult for people who are used to that old type of science. They spend so much time discussing whether an idea makes sense. They check the visualizations and noodle over it. That is all actively unhelpful."
Regarding the quantitative vs. qualitative discussion you mentioned that not everything could be quantified in measuring preferences and you have to rely on gut feelings. Well, you can quantify this gut feeling by asking people to rate their overall impression from the person, or how happy they are to have this particular car. Just because other quantifiable measures are not good predictors that does not mean that there aren't at all.
ReplyDelete