The team fed their algorithm datasets from recommendation engines Movielens and Jester. Essentially, their math weighs the value users get by clicking against the personal info they're disclosing, and points out when users would be handing over too much information for too little effect. While not everyone uses those particular services, they've definitely used a recommendation before if they've spun up a Pandora station or let Netflix suggest films.
Of course, since these are academics, their paper goes a step further, applying game theory to the algorithm's results in order to develop clicking strategies for the average internet browser to adopt. At best, following a shrewd strategy means a little over 5 percent of clicking certain things sides heavily in the user's favor. On the other side of the equation, it identifies 16 percent of clicks that would hand over much more personal info with very little gained.
Lead researcher on the team Mahsa Taziki plans to keep developing the system. She wants to implement it into a browser extension that would warn users when the website they're on is being too liberal with their personal data.