Original image
Getty Images

Crime Doesn't Pay (Well): The Economics of Bank Robberies

Original image
Getty Images

Hollywood always makes bank robberies look so easy (with some notable exceptions). You do a little planning, throw on a Richard Nixon mask, you’re in and out in a few minutes and then you can live the rest of your life in luxury in some tropical paradise that won’t extradite you.

A real-world bank job, however, isn’t a one-way ticket to luxury.

As economists Barry Reilly, Neil Rickman and Robert Witt explain in a new study, “The return on an average bank robbery is, frankly, rubbish.”

A UK banking organization asked the three to analyze the economic effectiveness of adding some new security measures to bank branches. As part of that, the guys had a little fun and took a look at the economics of bank robbery from the bad guys’ perspective. Their results are hardly the glamorous kind which movies have taught us to expect.

The first problem is that the typical return on a bank robbery is pretty modest. Over a three-year period, one thing or another went wrong and 1/3 of UK bank robbers got away with no money at all. The average haul for a successful heist was around £30,000 (or about $47,000). Even then, about 1/5 of successful robbers were later caught, arrested and convicted, and in some cases the money recovered.

The economists did discover a few ways that would-be Dillingers could increase their gains. Their data showed that each additional member of a robbery crew raises the expected value of the haul by £9,033.20 (~ $14,216 USD). “A larger gang may have spent more time on planning and reconnoitering,” they write. “In short, it may be more professional, and the larger returns may reflect that.” A large crew has one obvious drawback, though: there are more people that have to split the loot. If the crew divvies out the cash equally, “although the total haul goes up, the haul per person goes down.”

They also found that packing heat has a positive effect on the take, and “the threat of firearm use in a bank raid raises the unconditional expected value of the robbery by £10,300.50 [$16,210 USD],” on average.

No Way to Live

Given the average haul of £30,000 and the average full-time UK employment wage of about £26,000, the economists decided that typical bank robbers are not setting themselves up for a life of luxury. Rather, a heist “will give him a modest life-style for no more than 6 months.” The loss to the bank is so low, they say, that it “is not worth the banks’ while to spend as little as £4,500 per cashier position at every branch on [new security features] to deter [robberies].”

But that’s just a one-time job. What if you made a career of knocking over banks? That introduces a different problem. If someone keeps at it and robs two banks a year to maintain their income, the economists say, the odds of getting caught will increase. After three jobs, or a year and a half, his chance of getting busted is about half. One more job, and he’s very likely in prison, which really wreaks havoc on his earning potential.

“As a profitable occupation,” the study concludes, “bank robbery leaves a lot to be desired.”

Original image
iStock // Ekaterina Minaeva
Man Buys Two Metric Tons of LEGO Bricks; Sorts Them Via Machine Learning
May 21, 2017
Original image
iStock // Ekaterina Minaeva

Jacques Mattheij made a small, but awesome, mistake. He went on eBay one evening and bid on a bunch of bulk LEGO brick auctions, then went to sleep. Upon waking, he discovered that he was the high bidder on many, and was now the proud owner of two tons of LEGO bricks. (This is about 4400 pounds.) He wrote, "[L]esson 1: if you win almost all bids you are bidding too high."

Mattheij had noticed that bulk, unsorted bricks sell for something like €10/kilogram, whereas sets are roughly €40/kg and rare parts go for up to €100/kg. Much of the value of the bricks is in their sorting. If he could reduce the entropy of these bins of unsorted bricks, he could make a tidy profit. While many people do this work by hand, the problem is enormous—just the kind of challenge for a computer. Mattheij writes:

There are 38000+ shapes and there are 100+ possible shades of color (you can roughly tell how old someone is by asking them what lego colors they remember from their youth).

In the following months, Mattheij built a proof-of-concept sorting system using, of course, LEGO. He broke the problem down into a series of sub-problems (including "feeding LEGO reliably from a hopper is surprisingly hard," one of those facts of nature that will stymie even the best system design). After tinkering with the prototype at length, he expanded the system to a surprisingly complex system of conveyer belts (powered by a home treadmill), various pieces of cabinetry, and "copious quantities of crazy glue."

Here's a video showing the current system running at low speed:

The key part of the system was running the bricks past a camera paired with a computer running a neural net-based image classifier. That allows the computer (when sufficiently trained on brick images) to recognize bricks and thus categorize them by color, shape, or other parameters. Remember that as bricks pass by, they can be in any orientation, can be dirty, can even be stuck to other pieces. So having a flexible software system is key to recognizing—in a fraction of a second—what a given brick is, in order to sort it out. When a match is found, a jet of compressed air pops the piece off the conveyer belt and into a waiting bin.

After much experimentation, Mattheij rewrote the software (several times in fact) to accomplish a variety of basic tasks. At its core, the system takes images from a webcam and feeds them to a neural network to do the classification. Of course, the neural net needs to be "trained" by showing it lots of images, and telling it what those images represent. Mattheij's breakthrough was allowing the machine to effectively train itself, with guidance: Running pieces through allows the system to take its own photos, make a guess, and build on that guess. As long as Mattheij corrects the incorrect guesses, he ends up with a decent (and self-reinforcing) corpus of training data. As the machine continues running, it can rack up more training, allowing it to recognize a broad variety of pieces on the fly.

Here's another video, focusing on how the pieces move on conveyer belts (running at slow speed so puny humans can follow). You can also see the air jets in action:

In an email interview, Mattheij told Mental Floss that the system currently sorts LEGO bricks into more than 50 categories. It can also be run in a color-sorting mode to bin the parts across 12 color groups. (Thus at present you'd likely do a two-pass sort on the bricks: once for shape, then a separate pass for color.) He continues to refine the system, with a focus on making its recognition abilities faster. At some point down the line, he plans to make the software portion open source. You're on your own as far as building conveyer belts, bins, and so forth.

Check out Mattheij's writeup in two parts for more information. It starts with an overview of the story, followed up with a deep dive on the software. He's also tweeting about the project (among other things). And if you look around a bit, you'll find bulk LEGO brick auctions online—it's definitely a thing!

Original image
Name the Author Based on the Character
May 23, 2017
Original image