Do you ever stop and think about how much time you spend on your mobile phone, or binge-watching your favourite TV show? Could you predict how much time that will be tomorrow, or the next day, or the next week?
Not surprisingly, tech companies and apps actually make those predictions - and they also sell those predictions. And if companies are in the business of selling predictions, won’t they make more money if they can show their predictions are really good?
In this episode, we talk with Distinguished Professor Galit Shmueli who looked into this question - and uncovered a disturbing answer. What if, she thought, companies took it a step further by also getting us to do what they were predicting - or at least push us closer to our predicted behaviour?
In this episode, we talk to Galit about what she’s uncovered, how she’s using statistics and data science to really explain it, and what we can do about it.
Subscribe and listen to the podcast for free on iTunes, in Spotify, or on your Android device.
BONUS TRACK FROM GALIT'S INTERVIEW:
-
Galit talks about the varied lens by which different disciplines see the world, and what that means from a data science and statistics perspective.
ADDITIONAL LINKS
-
Paper on arXiv: "Improving" prediction of human behavior using behavior modification
-
Galit's personal web page: https://www.galitshmueli.com/