University of Arizona Tracks Student ID Card Swipes To Detect Who Might Drop Out

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.

Soooo...help me out here

[xevioso]

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.

Re:Soooo...help me out here

[Scarred Intellect]

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.

Re:

[xevioso]

It says, "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"

So they are basing their predictions on certain behavior of the students. What specifically is that behavior?

Re:Soooo...help me out here

[CrimsonAvenger]

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!

Re:

[RightwingNutjob]

Physical security. When I go to work, I badge in when I enter and badge in when I leave. Some lab spaces with sensitive equipment are access-controlled and you badge in to enter those too.

Do you have to type in your password to get at your netflix or amazon? Same idea...except in real life.

Re:

[NoSleepDemon]

The University I worked at used them for the purposes of restricting access to certain areas, depending on what you were studying or who you worked for. For example, Comp-Sci students got access to some of the more specialized computer labs. IT guys had access to server rooms etc. (can you guess what I was? :) It was also, apparently, possible to tell who was in the building during a fire, but I don't know how easily that information could be obtained during an actual blaze...

Re:

[mikael]

In my undergraduate course, we started out with around 30 students. It was known at the time at that department, that in any course, around 2 students drop out each year. This happened each year for 4+ years. They wouldn't turn up for tutorial/lab sessions, miss lectures, spend more time at the student union drinking/gaming at the pool tables or the library when they should have been doing courseworks.

Our university for legal reasons, kept a role call for every lecture and tutorial session. Other universiti

Re:

[known_coward_69]

not going to class would be a big one

student athletes miss a lot of it make to final 4

[Joe_Dragon]

student athletes miss a lot of it. Hell if they make to the final 4 then that a lot + time missed to get it.

Re:

[alvinrod]

Most universities have athletics departments that make sure their students are going to class and doing their work because they have academic eligibility requirements. Sure, if you're a school that's in the top ten it wouldn't surprise me if that gets bent a bit or that the university has shuffled those athletes into underwater basket weaving degrees that aren't particularly rigorous, but it isn't happening for the vast majority of athletes at the majority of institutions.

The only programs generating mil

Re:

[rtb61]

Millions of tax free dollars but wait, exactly why the fuck are they tax free dollars if the jock strap douche baggery has nothing what so ever to do with education.

Re:

[parkinglot777]

They also generate millions of dollars in revenue for the school...

If the sport is football and the school is doing average to good, then the school would be profiting. Basketball? Your school needs to do well or no profit. Baseball? Not so much. Though, not every school has a football team. Besides, not every school has a good sport team. As a result, not many schools are actually making money if you are talking about number of schools in the US.

Re:

[omnichad]

Something tells me that this person, employed by the university, considers that a future trade secret when they try to commercialize nationwide.

Re:

[AHuxley]

Think of what could be looked back and recovered about a person looking for a job.
Did they study a lot to get their good grades?
Library time? Lab time?
Speed too much time on the political and art student side of campus?
Off campus doing other things?
Still managed to get "given" good grades but the movements show a student who never really attended much "university"?

Easy

[Vinegar Joe]

I'd drop out of any school that followed me around like this. And once upon a time I was in grad school at UA.

Re:

[omnichad]

Although like most states, they have state funding cuts to deal with, they are still using more than tuition dollars. Not wasting grants/endowment returns and state money is all part of this. In a sense, the student is also the product, since they're not footing the whole bill.

Re:

[Anonymous Coward]

Although like most states, they have state funding cuts to deal with,

Lies, lies, lies.

The Real Reason College Tuition Costs So Much [nytimes.com]

In fact, public investment in higher education in America is vastly larger today, in inflation-adjusted dollars, than it was during the supposed golden age of public funding in the 1960s. Such spending has increased at a much faster rate than government spending in general. For example, the military’s budget is about 1.8 times higher today than it was in 1960, while legislative appropriations to higher education are more than 10 times high

Re:

[omnichad]

public investment in higher education in America is vastly larger today, in inflation-adjusted dollars

What about student-population adjusted dollars? There are more students in college today - both due to population growth and higher college attendance rates.

Re:

[godrik]

Read the article, it talks about that too. The article claims the $/student is higher than in the 60s, but dropped somewhat from the 90s.
Also the article claims that the administrative layers became bloated in the universities.

This match what I see in practice; though I haven't crunched numbers.
There is less money per student than there used to be; I wasn't around in the 60s but it certainly feels like there is funds than 20 years ago.
Also a lot of funds these days go to what I would call non academic expen

Re:

[RightwingNutjob]

It isn't, especially when the grade inflation is so bad the most commonly awarded grade is an A.

Re:

[alvinrod]

I don't think that's a problem if the content hasn't been dumbed down to make it possible for no effort on the part of most people to be able to get an A. Distributing the grading so that only a certain percentage can get an A is utterly pointless. I had a statistics class like that where the professor did something like that and it was practically impossible to get anything other than a D, C, or B. This resulted in a lot of people who had very similar grades (and a good understanding of the content) but it

Re:

[godrik]

I doubt this is good enough. There is grade inflation of course.
But I don't think that it is the real problem. You only get grades twice a year because most universities are on a semester system.
Therefore, it could take a year before you actually get the data you need to make a decision. By then it is probably too late.

The problem is that grades won't make the difference between:
-These were really tough classes for me.
-I got sick and could not quite follow.
-my mom lost her job and I needed to start working

Re:

[Opportunist]

So school does prepare for life. Because out in the real world, nobody gives a fuck which of the three was your reason to not perform as expected either.

Re:

[AHuxley]

AC a person who studied and used the library and lab a lot might have good grades.
A person who did not use the library and lab much might also have good "grades".
Nice to have another way of considering who to hire.

No information

[VorpalRodent]

Okay, I was going to dump on this, because the TheVerge article sucks. The press release, however, actually does a good job discussing some of the signals they track and how this ties into them. They even have a nice visualization of student traffic which hints at some ways that they might be able to infer stuff from all of it.

As an aside, the article contains this horrible quote (I really hope there's some missing context):

We think ...[we're] sort of doing what Amazon does — delivering items you didn't order but will be ordering in the future

I'm sorry, but I do not recall Amazon ever doing that. Quite frankly, I'd consider it really awkward to receive things in the mail based on what they thought I might need.

Re:No information

[omnichad]

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. [techcrunch.com]

Re:

[Anonymous Coward]

This is probably the real case of what amazon does. I'm sure by now they have pretty good stats on the things that customers may search for and add to their carts for later purchase, or just search for but don't add to a cart. They probably even have stats down to the individual of how likely you are to purchase something that you have saved for later or just searched for. They can optimize their delivery network on this data and move items closer to the purchasers before a purchase is ever made.

Re:

[will_die]

No major company is going to send unrequested items because under USA law that would be a gift so you can keep it. There have been some cases of smaller companies with high price low manufacturing cost, such as software, that have tried it and then bully the people into paying.
They are mixing up the fake story the New York Times created about Target doing that with baby advertisements.

Re:

[Actually, I do RTFA]

Wait, that Target story was fake? Documentation please...

why do I have to go an big lecture class (filler)

[Joe_Dragon]

why do I have to go an big lecture class even more so for the filler ones or ones where you just need cram for the test. I want to take classes I want to learn and not stuff I will never use.

Re:

[tlhIngan]

why do I have to go an big lecture class even more so for the filler ones or ones where you just need cram for the test. I want to take classes I want to learn and not stuff I will never use.

Because it's a university. If you just want to learn what you want to learn, take a trade school.

University students are expected to take courses (ok, forced) in non-subject areas, usually called "complimentary studies" or other terminology. This helps produce more well-rounded students who have a breadth of knowledge r

Re:

[demonlapin]

This helps produce more well-rounded students who have a breadth of knowledge rather than a rather narrow specialized field.

That's certainly the concept, but AIUI European universities don't do anything like this, and their graduates don't seem to have a worse general fund of knowledge than equally-educated Americans. I sure as hell didn't get all that much out of my "distributional" requirements. The really interesting stuff that was outside my major didn't count toward them - I think I was one class away from a minor in classics when I graduated.

Re:

[demonlapin]

That has more to do with the kind of people who get into Harvard or Yale than the kind of education that goes on there.

Re:

[AHuxley]

So a boss and company, gov, mil knows a person wanting a job later can study and showed they can be punctual and can manage time.

Re:

[Opportunist]

How, by having my card at certain places at certain times? If anything, it proves that I can get people to do stuff for me.

Use Bayesian

[Darkness Of Course]

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.

Re:

[RightwingNutjob]

The SAT and ACT are good predictors. I suppose you could ace them even if you hate school with a burning passion, and many people do. But few people who hate it enough to drop out would bother to.

Re:

[RightwingNutjob]

I didn't say it was perfect, but I am pretty sure that someone who gets a 25th percentile SAT score ain't gonna last too long at a top-25 university, no matter what rocks-for-jocks major he tries to slink through with. It won't catch the 1600 SAT nerd who drops out after two years to start a billion-dollar business, and it won't catch the type-A overachiever who has a mental breakdown after three semesters of 72 credit-hours and zero sleep hours a pop, but standardized tests have their place, along with gra

politics-free?

[supernova87a]

I'm surprised that the researchers didn't start to run into university politics before they published their result -- namely, that the University is using data to segregate students and preferentially help some students and not others.

Many a data science / predictive algorithm study has been sunk because university administrators think it singles out people, even if it is to help them.

We have this system

[mrwireless]

Systems like this are everywhere now.

For example, here in the Netherlands a similar system is used in Dordrecht. It's extremely untransparant, where the makers say they want to avoid the hassle of a public debate..
Source: https://www.groene.nl/artikel/... [groene.nl]

China is another obvious example. They use data to pinpoint students with potential psychological issues.
Source: https://www.volkskrant.nl/buit... [volkskrant.nl]

Big data is feeding our impulse to be risk averse. The question is what this does to students in th

Re:

[Opportunist]

It will do to students what such systems always do: It makes them find out how to game the system. Once it's out that you should spend time in the library, people will hand their cards to their dorm partners who need to research something in the library to soak up some "I'm studying hard" points while sleeping off last night's party.

Give the whole shit 2 years and they'll find out that students are one demographic that's really resistant to profiling.

Tutors?

[TJHook3r]

I get that students are responsible adults but when they are paying tens of thousands for their education, surely their tutors should be the ones noticing this, not a data mining operation?