Here’s what I’ve spent the last couple of days doing: alternatively reading Christian Rudder’s new book Dataclysm and proofreading a report by AAPOR which discusses the benefits, dangers, and ethics of using big data, which is mostly “found” data originally meant for some other purpose, as a replacement for public surveys, with their carefully constructed data collection processes and informed consent. The AAPOR folk have asked me to provide tangible examples of the dangers of using big data to infer things about public opinion, and I am tempted to simply ask them all to read Dataclysm as exhibit A.
Rudder is a co-founder of OKCupid, an online dating site. His book mainly pertains to how people search for love and sex online, and how they represent themselves in their profiles.
Here’s something that I will mention for context into his data explorations: Rudder likes to crudely provoke, as he displayed when he wrote this recent post explaining how OKCupid experiments on users. He enjoys playing the part of the somewhat creepy detective, peering into what OKCupid users thought was a somewhat private place to prepare themselves for the dating world. It’s the online equivalent of a video camera in a changing booth at a department store, which he defended not-so-subtly on a recent NPR show called On The Media, and which was written up here.
I won’t dwell on that aspect of the story because I think it’s a good and timely conversation, and I’m glad the public is finally waking up to what I’ve known for years is going on. I’m actually happy Rudder is so nonchalant about it because there’s no pretense.
Even so, I’m less happy with his actual data work. Let me tell you why I say that with a few examples.
Who are OKCupid users?
I spent a lot of time with my students this summer saying that a standalone number wouldn’t be interesting, that you have to compare that number to some baseline that people can understand. So if I told you how many black kids have been stopped and frisked this year in NYC, I’d also need to tell you how many black kids live in NYC for you to get an idea of the scope of the issue. It’s a basic fact about data analysis and reporting.
When you’re dealing with populations on dating sites and you want to conclude things about the larger culture, the relevant “baseline comparison” is how well the members of the dating site represent the population as a whole. Rudder doesn’t do this. Instead he just says there are lots of OKCupid users for the first few chapters, and then later on after he’s made a few spectacularly broad statements, on page 104 he compares the users of OKCupid to the wider internet users, but not to the general population.
It’s an inappropriate baseline, made too late. Because I’m not sure about you but I don’t have a keen sense of the population of internet users. I’m pretty sure very young kids and old people are not well represented, but that’s about it. My students would have known to compare a population to the census. It needs to happen.
How do you collect your data?
Let me back up to the very beginning of the book, where Rudder startles us by showing us that the men that women rate “most attractive” are about their age whereas the women that men rate “most attractive” are consistently 20 years old, no matter how old the men are.
Actually, I am projecting. Rudder never actually specifically tells us what the rating is, how it’s exactly worded, and how the profiles are presented to the different groups. And that’s a problem, which he ignores completely until much later in the book when he mentions that how survey questions are worded can have a profound effect on how people respond, but his target is someone else’s survey, not his OKCupid environment.
Words matter, and they matter differently for men and women. So for example, if there were a button for “eye candy,” we might expect women to choose more young men. If my guess is correct, and the term in use is “most attractive”, then for men it might well trigger a sexual concept whereas for women it might trigger a different social construct; indeed I would assume it does.
Since this isn’t a porn site, it’s a dating site, we are not filtering for purely visual appeal; we are looking for relationships. We are thinking beyond what turns us on physically and asking ourselves, who would we want to spend time with? Who would our family like us to be with? Who would make us be attractive to ourselves? Those are different questions and provoke different answers. And they are culturally interesting questions, which Rudder never explores. A lost opportunity.
Next, how does the recommendation engine work? I can well imagine that, once you’ve rated Profile A high, there is an algorithm that finds Profile B such that “people who liked Profile A also liked Profile B”. If so, then there’s yet another reason to worry that such results as Rudder described are produced in part as a result of the feedback loop engendered by the recommendation engine. But he doesn’t explain how his data is collected, how it is prompted, or the exact words that are used.
Here’s a clue that Rudder is confused by his own facile interpretations: men and women both state that they are looking for relationships with people around their own age or slightly younger, and that they end up messaging people slightly younger than they are but not many many years younger. So forty year old men do not message twenty year old women.
Is this sad sexual frustration? Is this, in Rudder’s words, the difference between what they claim they want and what they really want behind closed doors? Not at all. This is more likely the difference between how we live our fantasies and how we actually realistically see our future.
Need to control for population
Here’s another frustrating bit from the book: Rudder talks about how hard it is for older people to get a date but he doesn’t correct for population. And since he never tells us how many OKCupid users are older, nor does he compare his users to the census, I cannot infer this.
Here’s a graph from Rudder’s book showing the age of men who respond to women’s profiles of various ages:
We’re meant to be impressed with Rudder’s line, “for every 100 men interested in that twenty year old, there are only 9 looking for someone thirty years older.” But here’s the thing, maybe there are 20 times as many 20-year-olds as there are 50-year-olds on the site? In which case, yay for the 50-year-old chicks? After all, those histograms look pretty healthy in shape, and they might be differently sized because the population size itself is drastically different for different ages.
One of the worst examples of statistical mistakes is his experiment in turning off pictures. Rudder ignores the concept of confounders altogether, which he again miraculously is aware of in the next chapter on race.
To be more precise, Rudder talks about the experiment when OKCupid turned off pictures. Most people went away when this happened but certain people did not:
Some of the people who stayed on went on a “blind date.” Those people, which Rudder called the “intrepid few,” had a good time with people no matter how unattractive they were deemed to be based on OKCupid’s system of attractiveness. His conclusion: people are preselecting for attractiveness, which is actually unimportant to them.
But here’s the thing, that’s only true for people who were willing to go on blind dates. What he’s done is select for people who are not superficial about looks, and then collect data that suggests they are not superficial about looks. That doesn’t mean that OKCupid users as a whole are not superficial about looks. The ones that are just got the hell out when the pictures went dark.
This brings me to the most interesting part of the book, where Rudder explores race. Again, it ends up being too blunt by far.
Here’s the thing. Race is a big deal in this country, and racism is a heavy criticism to be firing at people, so you need to be careful, and that’s a good thing, because it’s important. The way Rudder throws it around is careless, and he risks rendering the term meaningless by not having a careful discussion. The frustrating part is that I think he actually has the data to have a very good discussion, but he just doesn’t make the case the way it’s written.
Rudder pulls together stats on how men of all races rate women of all races on an attractiveness scale of 1-5. It shows that non-black men find their own race attractive and non-black men find black women, in general, less attractive. Interesting, especially when you immediately follow that up with similar stats from other U.S. dating sites and – most importantly – with the fact that outside the U.S., we do not see this pattern. Unfortunately that crucial fact is buried at the end of the chapter, and instead we get this embarrassing quote right after the opening stats:
And an unintentionally hilarious 84 percent of users answered this match question:
Would you consider dating someone who has vocalized a strong negative bias toward a certain race of people?
in the absolute negative (choosing “No” over “Yes” and “It depends”). In light of the previous data, that means 84 percent of people on OKCupid would not consider dating someone on OKCupid.
Here Rudder just completely loses me. Am I “vocalizing” a strong negative bias towards black women if I am a white man who finds white women and asian women hot?
Especially if you consider that, as consumers of social platforms and sites like OKCupid, we are trained to rank all the products we come across to ultimately get better offerings, it is a step too far for the detective on the other side of the camera to turn around and point fingers at us for doing what we’re told. Indeed, this sentence plunges Rudder’s narrative deeply into the creepy and provocative territory, and he never fully returns, nor does he seem to want to. Rudder seems to confuse provocation for thoughtfulness.
This is, again, a shame. A careful conversation about the issues of what we are attracted to, what we can imagine doing, and how we might imagine that will look to our wider audience, and how our culture informs those imaginings, are all in play here, and could have been drawn out in a non-accusatory and much more useful way.
Do you know what I am doing this morning? I’m glued to ESPN talk radio, which is 98.7FM in the NYC area, although it is a national station and can be streamed online as well.
Here’s a statement you might be surprised to hear from me. In the past decade, sports talk radio has become the best, rawest, and most honest source of information about how our culture condones and ignores violence against women, not to mention issues of race and homophobia. True fact. You are not going to hear this stuff from politicians or academics.
The specific trigger for the conversation today is the fact that NFL football player Ray Rice has been indefinitely suspended from playing now that a video has emerged of him beating his wife in the elevator. Previously we had only gotten to seen the video of her slumped body after he came out of the elevator with her. The police didn’t do much about it, and then the NFL responded with a paltry 2-game suspension, after which there was such a backlash (partly through sports radio!) that the commissioner promised to enact a stronger policy.
Questions being addressed right now as I type:
- Why didn’t the police give Rice a bigger penalty for beating his wife unconscious?
- Why didn’t the NFL ask for that video before now? Or did they, and now they’re lying?
- What does it say about the NFL that they had the wife, Janay Rice, apologize for her role in the incident?
- What did people think it would look like when a professional football player knocks out a woman?
- Did people really think she did something to deserve it, and now they are shocked to see that she didn’t?
I’m very gratified to say that my Lede Program for data journalism at Columbia is over, or at least the summer program is (some students go on to take Computer Science classes in the Fall).
My adorable and brilliant students gave final presentations on Tuesday and then we had a celebration Tuesday night at my house, and my bluegrass band played (didn’t know I have a bluegrass band? I play the fiddle! You can follow us on twitter!). It was awesome! I’m hoping to get some of their projects online soon, and I’ll definitely link to it when that happens.
It’s been an exciting week, and needless to say I’m exhausted. So instead of a frothy rant I’ll just share some reading with y’all:
- Andrew Gelman has a guest post by Phil Price on the worst infographic ever, which sadly comes from Vox. My students all know better than this. Hat tip Lambert Strether.
- Private equity firms are buying stuff all over the country, including Ferguson. I’m actually not sure this is a bad thing, though, if nobody else is willing to do it. Please discuss.
- Bloomberg has an interesting story about online PayDay loans and the world of investing. I am still on the search for someone who knows exactly how those guys target their ads online. Hat tip Aryt Alasti.
- Felix Salmon, now at Fusion, has set up a nifty interactive to help you figure out your lifetime earnings.
- Felix also set up this cool online game where you can play as a debt collector or a debtor.
- Is it time to end letter grades? Hat tip Rebecca Murphy.
- There’s a reason fast food workers are striking nationwide. The ratio of average CEO pay to average full-time worker pay is around 1252.
- People lie to women in negotiations. I need to remember this.
Have a great weekend!
I’ve been sent this recent New York Times article by a few people (thanks!). It’s called Grading Teachers, With Data From Class, and it’s about how standardized tests are showing themselves to be inadequate to evaluate teachers, so a Silicon Valley-backed education startup called Panorama is stepping into the mix with a data collection process focused on student evaluations.
Putting aside for now how much this is a play for collecting information about the students themselves, I have a few words to say about the signal which one gets from student evaluations. It’s noisy.
So, for example, I was a calculus teacher at Barnard, teaching students from all over the Columbia University community (so, not just women). I taught the same class two semesters in a row: first in Fall, then in Spring.
Here’s something I noticed. The students in the Fall were young (mostly first semester frosh), eager, smart, and hard-working. They loved me and gave me high marks on all categories, except of course for the few students who just hated math, who would typically give themselves away by saying “I hate math and this class is no different.”
The students in the Spring were older, less eager, probably just as smart, but less hard-working. They didn’t like me or the class. In particular, they didn’t like how I expected them to work hard and challenge themselves. The evaluations came back consistently less excited, with many more people who hated math.
I figured out that many of the students had avoided this class and were taking it for a requirement, didn’t want to be there, and it showed. And the result was that, although my teaching didn’t change remarkably between the two semesters, my evaluations changed considerably.
Was there some way I could have gotten better evaluations from that second group? Absolutely. I could have made the class easier. That class wanted calculus to be cookie-cutter, and didn’t particularly care about the underlying concepts and didn’t want to challenge themselves. The first class, by contrast, had loved those things.
My conclusion is that, once we add “get good student evaluations” to the mix of requirements for our country’s teachers, we are asking for them to conform to their students’ wishes, which aren’t always good. Many of the students in this country don’t like doing homework (in fact most!). Only some of them like to be challenged to think outside their comfort zone. We think teachers should do those things, but by asking them to get good student evaluations we might be preventing them from doing those things. A bad feedback loop would result.
I’m not saying teachers shouldn’t look at student evaluations; far from it, I always did and I found them useful and illuminating, but the data was very noisy. I’d love to see teachers be allowed to see these evaluations without there being punitive consequences.
“Data Science” is one of my least favorite tech buzzwords, second to probably “Big Data”, which in my opinion should be always printed followed by a winky face (after all, my data is bigger than yours). It’s mostly a marketing ploy used by companies to attract talented scientists, statisticians, and mathematicians, who, at the end of the day, will probably be working on some sort of advertising problem or the other.
Still, you have to admit, it does have a nice ring to it. Thus the title Democratizing Data Science, a vision paper which I co-authored with two cool Ph.D students at MIT CSAIL, William Li and Ramesh Sridharan.
The paper focuses on the latter part of the situation mentioned above. Namely, how can we direct these data scientists, aka scientists who interact with the data pipeline throughout the problem-solving process (whether they be computer scientists or programmers or statisticians or mathematicians in practice) towards problems focused on societal issues?
In the paper, we briefly define Data Science (asking ourselves what the heck it even means), then question what it means to democratize the field, and to what end that may be achieved. In other words, the current applications of Data Science, a new but growing field, in both research and industry, has the potential for great social impact, but in reality, resources are rarely distributed in a way to optimize the social good.
We’ll be presenting the paper at the KDD Conference next Sunday, August 24th at 11am as a highlight talk in the Bloomberg Building, 731 Lexington Avenue, NY, NY. It will be more like an open conversation than a lecture and audience participation and opinion is very welcome.
The conference on Sunday at Bloomberg is free, although you do need to register. There are three “tracks” going on that morning, “Data Science & Policy”, “Urban Computing”, and “Data Frameworks”. Ours is in the 3rd track. Sign up here!
If you don’t have time to make it, give the paper a skim anyway, because if you’re on Mathbabe’s blog you probably care about some of these things we talk about.
There was a recent New York Times op-ed by Sonja Starr entitled Sentencing, by the Numbers (hat tip Jordan Ellenberg and Linda Brown) which described the widespread use – in 20 states so far and growing – of predictive models in sentencing.
The idea is to use a risk score to help inform sentencing of offenders. The risk is, I guess, supposed to tell us how likely the person is to commit another act in the future, although that’s not specified. From the article:
The basic problem is that the risk scores are not based on the defendant’s crime. They are primarily or wholly based on prior characteristics: criminal history (a legitimate criterion), but also factors unrelated to conduct. Specifics vary across states, but common factors include unemployment, marital status, age, education, finances, neighborhood, and family background, including family members’ criminal history.
I knew about the existence of such models, at least in the context of prisoners with mental disorders in England, but I didn’t know how widespread it had become here. This is a great example of a weapon of math destruction and I will be using this in my book.
A few comments:
- I’ll start with the good news. It is unconstitutional to use information such as family member’s criminal history against someone. Eric Holder is fighting against the use of such models.
- It is also presumably unconstitutional to jail someone longer for being poor, which is what this effectively does. The article has good examples of this.
- The modelers defend this crap as “scientific,” which is the worst abuse of science and mathematics imaginable.
- The people using this claim they only use it for as a way to mitigate sentencing, but letting a bunch of rich white people off easier because they are not considered “high risk” is tantamount to sentencing poor minorities more.
- It is a great example of confused causality. We could easily imagine a certain group that gets arrested more often for a given crime (poor black men, marijuana possession) just because the police have that practice for whatever reason (Stop & Frisk). Then model would then consider any such man at a higher risk of repeat offending, but that’s not because any particular person is actually more likely to do it, but because the police are more likely to arrest that person for it.
- It also creates a negative feedback loop on the most vulnerable population: the model will impose longer sentencing on the population it considers most risky, which will in turn make them even riskier in the future, if “length of time in prison previously” is used as an attribute in the model, which is surely is.
- Not to be cynical, but considering my post yesterday, I’m not sure how much momentum will be created to stop the use of such models, considering how discriminatory it is.
- Here’s an extreme example of preferential sentencing which already happens: rich dude Robert H Richards IV raped his 3-year-old daughter and didn’t go to jail because the judge ruled he “wouldn’t fare well in prison.”
- How great would it be if we used data and models to make sure rich people went to jail just as often and for just as long as poor people for the same crime, instead of the other way around?
I’ve been fascinated to learn all sorts of things about how McDonalds operates their business in the past few days, as news broke about a recent NLRB decision to allow certain people who work in McDonalds to file complaints about their workplace and name McDonalds as a joint employer.
That sounds incredibly dull, right? The idea of letting McDonalds workers name McDonalds as an employer? Let me tell you a bit more. And this is all common knowledge, but I thought I’d gather it here for those of you who haven’t been following the story.
Most of the McDonalds joints you go to are franchises – 90% in this country. That means the business is owned by a franchisee, a person who pays good money (details here) for the right to run a McDonalds and is constrained by a huge long list of rules about how they have to do it.
The franchise owner attends Hamburger University and gets trained in all sorts of things, like exactly how things should look in the store, how customers should be funneled through space (maps included), how long each thing should take, and how to treat employees. There’s a QSC Playbook they are given (Quality, Service, and Cleanliness) as well as minute descriptions of how to organize their teams and even the vocabulary words they should use to encourage workers (see page 24 of the Shift Management Guide I found online here).
McDonalds also installs a real-time surveillance system into each McDonalds, which can calculate the rate of revenue brought in at a given moment, as well as the rate of pay going out, and when the ratio of those two numbers reaches a certain lower bound threshold, they encourage franchise owners to ask people to leave or delay people from clocking in. Encourage, mind you, not require. They are not the employers or anything remotely like that, clearly.
Take a step back here. What is the business model of a franchise? And when did McDonalds stop being a burger joint?
The idea is this. When you own a restaurant you have to deal with all these people who work for you and you have to deal with their complaints, and they might not like the way you treat them and they might organize against you or sue you. In order to contain your risks, you franchise. That effectively removes all of those people except one, the franchise owner, with whom you have an air-tight contract, written by a huge team of lawyers, which basically says that you get to cancel the franchise agreement for any minor infraction (where they’d lose a bunch of investment money), but most importantly it means the people actually working in a given franchise work for that one person, not for you, so their pesky legal issues are kept away from you. It’s a way to box in the legal risk of the parent company.
Restaurants aren’t the only business to learn that it’s easier to sell and manage a brand than it is to sell and manage an actual product. Hotels have been doing this for a long time, and avoid complaints and legal issues stemming from the huge population of service workers in hotels, mostly minority women.
For a copy of the original complaint that gave the details of McDonald’s control over workers, read this. For a better feel for being a McDonalds worker, please read this recent Reuters blog post written by a McDonalds worker. And for a better feel for being a McDonald’s franchise owner, read this recent Washington Post letter from a long-time McDonalds franchise owner who thinks workers are being unfairly treated.
Does that sounds confusing, that a franchise owner would side with the employees? It shouldn’t.
By nature of the franchise contract, the money actually available to a franchise owner is whatever’s left over after they pay McDonalds for advertising, and buy all the equipment and food that McDonalds tells them to from the sources that they tell them to, and after they pay for insurance on everything and for rent on the property (which McDonalds typically owns). In other words the only variable they have to tweak is the employer pay, but if they pay a living wage then they lose money on their business. In fact when franchise owners complain about the profit stream, McDonalds tells them to pay their workers less. McDonalds essentially controls everything except one variable, but since it’s a closed system of equations, that means the franchise owners have to decide between paying their workers reasonably and going in the red.
That’s not to say, of course, that McDonalds as an enterprise is at risk of losing money. In fact the parent corporation is making good money ($1.4 billion per quarter if you include international revenue), by squeezing the franchises. If the franchise owners had more leverage to negotiate better contracts, they could siphon off more revenue and then – possibly – share it with workers.
So back to the ruling. If upheld, and there’s a good chance it won’t be but I’m feeling hopeful today, this decision will allow people to point at McDonalds the corporation when they are treated badly, and will potentially allow a workers’ union to form. Alternatively it might energize the franchise owners to negotiate more flexible contracts, which could allow them to pay their workers better directly.