SuperFreakonomics Book Club: Can a Banker's Algorithm Help Catch Would-Be Terrorists?

The SuperFreakonomics Virtual Book Club invites readers to ask questions of some of the researchers and other characters in our book. (Earlier Q&A’s can be found here.)

This week we’re offering up “Ian Horsley.” By day, he is employed in the anti-fraud department of a large British bank; but in his every spare moment for the past few years he has been working hard in collaboration with Steve Levitt to build an algorithm that can identify potential terrorists by their retail banking data. A few excerpts:

He doesn’t work in law enforcement, or in government or the military, nor does anything in his background or manner suggest he might be the least bit heroic. He grew up in the heart of England, the son of an electrical engineer, and is now well into middle age. He still lives happily far from the maddening thrum of London. While perfectly affable, he isn’t outgoing or jolly by any measure; Horsley is, in his own words, “completely average and utterly forgettable.”


The procedure [to build the algorithm] would require two steps. First, assemble all the available data on these hundred-plus suspects [already arrested by British police after the 7/7 bombings] and create an algorithm based on the patterns that set these men apart from the general population. Once the algorithm was successfully fine-tuned, it could be used to dredge through the bank’s database to identify other potential bad guys. Given that the United Kingdom was battling Islamic fundamentalists and no longer, for instance, Irish militants, the arrested suspects invariably had Muslim names. This would turn out to be one of the strongest demographic markers for the algorithm.


There were also some prominent negative indicators. The data showed that a would-be terrorist was disproportionately unlikely to:

Have a savings account
Withdraw money from an ATM on a Friday afternoon
Buy life insurance

The no-ATM-on-Friday metric would seem to be a proxy for a Muslim who attends that day’s mandatory prayer service. The life-insurance marker is a bit more interesting. Let’s say you’re a twenty-six-year-old man, married with two young children. It probably makes sense to buy some life insurance so your family can survive if you happen to die young. But an insurance company may not pay out if the policyholder commits a suicide bombing. So a twenty-six-year-old family man who suspects he may one day blow himself up may not waste money on life insurance.


As of this writing, Horsley has handed off the list of 30 to his superiors, who in turn have handed it off to the proper authorities. Horsley has done his work; now it is time for them to do theirs. Given the nature of the problem, Horsley may never know for certain if he was successful. And you, the reader, are even less likely to see direct evidence of his success because it would be invisible, manifesting itself in terrorist attacks that never happen.

mike c.

I hope the algorithm is more sophisticated than described here. It sounds like a method for detecting observant Muslims, most of whom are of course not terrorists.

Camp Freddie

I found this to be one of the worst arguments in your book. All it selects for is devout muslims.

Savings accounts are usury and not permitted.
Friday prayer sessions are not just for jihadis, they're kind of a pillar of islam.
Life assurance is a form of gambling and not permitted.

Didn't the book also claim there was a super-secret 4th element to the algorithm that you couldn't reveal because of national security? That part really annoyed me when I read it, since I didn't appreciate being teased. On the strength of the other 3 examples I just didn't believe that some mysterious 4th variable would work (unless it's "are more likely than average to have bought industrial quantities of hair dye and nail varnish remover").

It sounds about as good as analysing for IRA terrorists by checking if they have made fewer than average low-value purchases from late-night chemists.

Ian Kemmish

Actually I may well find out if he's being taken seriously, because as I've mentioned several times, I pass (or fail?) way too many of the tests you've mentioned here from time to time. (One assumes that in order to be any use at all, the "live" data would have to be anonymised, so the bit about Muslim names would seem to apply only to training the algorithm in the first place.)

This algorithm, in my opinion, will throw up far too many false positives to be useful. It sounds like a neural network - and I'm reminded of the (possibly apocryphal) story of the neural network the Pentagon built to identify photos containing camouflaged tanks, only to discover that, because of poorly chosen training data, what they really had was a network which could identify photos taken on cloudy days.

And by the way - you can now get a reasonably wide variety of Sharia-compliant savings accounts and life insurance here in the UK, so those two parts of the test would appear to have become obsolete since they were first proposed....



Wow what a waste of time for him to do this when commercial companies abound which could provide it.

I bet that data mining, target market, and demographic research companies could have this done in about a couple of weeks by cross relating purchases to retail banking to residence locations etc.


I suspect all terrorists are now buying large quantities of life insurance.


the other reason for no life insurance may be to not raise any red flags (life insurance is usually taken out by spouses to cash in after the 'accident' anyway)

Drill-Baby-Drill Drill Team

Doing the Haj to Mecca in Saudi Arabia, is something all Muslims want to do before they die. Suicical people do gesture and unique behaviors such as giving away their dear poessessions, making a will and making peace with their relations. And if you were a Muslim Fanatic and were going on a Suicide Mission, it would be a nice gesture to Allah, to complete a Haj, just as Westerner would make sure all the insurance and paperwork is in order and the suicide note has been penned.

I wonder how many of the the 21 Suicide Bombers on 9/11 went on Haj in the months or year prior to the attack?

I would suggest keeping a Haj list of young Muslims, or at least passport control to Saudi Arabia, who may be prone to seek Paradise prematurely on a mission to send some infidels to hell.

Not too long ago bankers were the terrorists.

Can't we just keep hassling them based on their appearance alone?

Robert G.

Well, did you ever get any feedback? Does your "secret sauce" work?

John Ellis

Dismal science if ever there was.

If these people get arrested and tried then we hear about it. They do not have to actually blow anything up.

False positives? Any mass screening program like for prostate or breast cancer throws up so many false positives you have to be careful how you apply them. Similarly the security theatre at ariports.
So what is the false positive rate of this little fable then?
Has the technique been applied to an independent data set which wasn't used for the curve fitting and for which we have a good idea of the results? Eg, you could deliberately withhold the data of 2 known terrorists in the initial analysis and then see how they are subsequently classified.

In short is there any actual evidence for the effectiveness of this egregious piece of armchair anti-terrorism?


I like your books, just wanted to say that right of. I enjoy this site, and many things that deal with incentives. I am an Organizational Psych (OP) major, and think that there are some things that your approach can be applied to in the field, also something you might find interesting about OP.

I was wondering about incentives. In a lot of ways incentives create motivation and influence perception. However, I was wondering about how do you figure out incentives? Sure money is a big one, and some other resources relating to currency, but are incentives cultural in your opinion or are they general for all humans? Are some incentives for instance camoflauged to appear as one thing but are in reality another? I know instinctively the answers to most of these questions, as a general non-economist, but what does an economist think of these questions? and how would a freak-conomist answer them? Hopefully interesting.

Another intersting thing about incentives I find is purchases that have no basis other than appeal, iphone being a case. In most cases one doesn't need such a phone, yet there are millions among millions who feel that they do. What are your opinions on the matter? What is the incentive? and Why do we want them so badly? from a freakonomics perspective if you can please~



I really enjoyed this part of the book. Although a little creepy, I really enjoy profiling exercises. I like how human nature often betrays itself in ways we don't typically realize.

If I remember correctly, Ian obtained his job sort of by accident. How would one go about getting a job like his? What would Ian advise I do, to get a job similar to his or helping him?


Obvious problem:

Knowing this, now any potential terrorist reading this will be duty bound to withdraw funds from an ATM on Fridays, get a savings account, and purchase life insurance.

although, purchasing new underwear....if may see that in your data...may be quite signficant when correlated with other data points. but don't tell anyone about that point.


Can you get much unique information about people from bank records, which isn't already present in other data that law enforcement have access to? For instance, suppose that the British police had a long list of potential terrorism suspects, created from other data sources, and already knew that they were all observant Muslims. Would the bank data help to narrow this list down to a much smaller list of suspects who were especially likely to be terrorists, or would it mostly just be redundant with what the police already knew?


I'm an American. I have life insurnace through two different companies (one private and the other through my employer). I have several savings accounts with one bank and an investment account with an online brokerage.

What bothers me about this post is that there is supposedly a single database that not only contains all this information but also can quickly see whether or not I use my ATM card on Fridays! While there are obvious privacy concerns, a more practical concern is that such an algorithm seems to assume that we have access to such universal data. Do we?

E. Nowak

Wow, this is really chilling. How do you define a "potential terrorist?" Angry? Anti-American? Pro-violence? Well, you could say that about just about any Tea-Party person these days.

This is the problem with most statisticians I hear these days. They look at numbers and see "reality". But what they really see justifications for their prejudices.

Bah Hah

Gee, I must take a good look at myself. From the criteria described, I'm afraid I may be one of these frightening terrorists.

1. I am a Muslim who recently turned 26 with a wife and small child
2. No savings account - I use a line of credit
3. I don't use ATM on Friday - because I budget well and take my funds on Wednesday
4. I don't have life insurance - personal choice given my current investment strategies will see my family remain in a comfortable position for many years to come.

Please - where can I turn myself in?

Bob Iam

1. Identify Muslims.
2. ???
3. Profit!

I don't see how this methodology could fail.


these are just sections of the book. the algorithum involved much more then just these 4 variables. the terrorist data also showed they were disproportionately likely to "own a mobile phone, be a student, rent, rather than own, a home" and he also lists additional facts before about they were more likely to "use a P.O. box as an address" or "make on large deposit and then withdraw cash in small amounts" or "the ratio of cash withdrawals to checks written was unusually high". and there are more variables then that they even mention the big thing about variable x is that its a behavioral variable and measure the intesity of something rather then yes or no. and the book also doesn't say those 30 people were terrorists instead even Ian says that probably only 5 are involved. You aren't a terrorist if you fit this mold but terrorists are likely to fit this mold and the algorithim isn't perfect as they admit in the book. Additionally Ian used the data base information of his own bank not some global privacy destroyer database



also nobody has really asked Ian a question i realized.

what do you think of the use of algorithums by companies to find the best candidate of a pool of job applicants? i've heard of a couple companies attempt to do this.