Slashdot Mirror

← Back to Stories (view on slashdot.org)

University of Arizona Tracks Student ID Card Swipes To Detect Who Might Drop Out (theverge.com)

Posted by BeauHD on from the every-breath-you-take dept.

An anonymous reader quotes a report from The Verge: The University of Arizona is tracking freshman students' ID card swipes to anticipate which students are more likely to drop out. University researchers hope to use the data to lower dropout rates. (Dropping out refers to those who have left higher-education entirely and those who transfer to other colleges.) The card data tells researchers how frequently a student has entered a residence hall, library, and the student recreation center, which includes a salon, convenience store, mail room, and movie theater. The cards are also used for buying vending machine snacks and more, putting the total number of locations near 700. There's a sensor embedded in the CatCard student IDs, which are given to every student attending the university. Researchers have gathered freshman data over a three-year time frame so far, and they found that their predictions for who is more likely to drop out are 73 percent accurate. They also have plans to give academic advisers an online dashboard to look at student data in real time. "By getting their digital traces, you can explore their patterns of movement, behavior and interactions, and that tells you a great deal about them," Sudha Ram, a professor of management information systems who directs the initiative, said in a press release.

5 of 103 comments (clear)

  1. Soooo...help me out here by xevioso · · Score: 5, Insightful

    The article is void on information on what specific statistics indicate a student is more likely to drop out. Are students who use their ID card to go to the rec center more likely to drop out over students who us it to enter the library? The article doesn't say.

    1. Re:Soooo...help me out here by Scarred+Intellect · · Score: 3, Insightful

      That's probably exactly what they're trying to figure out. Only 3 years of data doesn't seem like much to get anything definitive, especially since those first students haven't even graduated yet. I image with a few more years of data they can refine it more and get something more definitive.

    2. Re:Soooo...help me out here by CrimsonAvenger · · Score: 4, Interesting

      they found that their predictions for who is more likely to drop out are 73 percent accurate"

      73% accurate is nothing to write home about. Especiakkt since they didn't give us a dropout rate.

      i.e. 10% dropout rate at73% accuracy will show 24+% of your students going to dropout when they have no such intentions. As well as another 7.3% who actually are going to dropout. While missing 2.7% who are going to dropout, but who have no such intentions.

      An accuracy rate of 73% is only useful (and not very useful even then) if the dropout rate is about 50-50 or better.

      And what's the deal with spying on your paying customers anyway? Jaysus, tracking every building on campus you enter? Yah, no doubt that'll be very useful for any rape investigations on campus, but really!

      --

      "I do not agree with what you say, but I will defend to the death your right to say it"
  2. Use Bayesian by Darkness+Of+Course · · Score: 3, Insightful

    Bayesian solutions should be capable of >80%.
    The alledged wisdom of the crowds should get close to Bayes.

    73% is a miss. They should take a class.

  3. Re:No information by omnichad · · Score: 5, Informative

    I'm sorry, but I do not recall Amazon ever doing that.

    Consider their regional warehouses like a giant edge cache. They pre-buffer likely products into that cache.