Geoprofiling Moves Into The Limelight

circletimessquare writes "Interesting and timely. A short piece at CNN talks about the software helping to track down the sniper currently terrorizing the Washington DC area. It was the doctoral thesis of a cop, Kim Rossmo, who developed it while walking the beat in Vancouver and reading about the hunting patterns of African lions. Googling, I found an older but deeper piece which mentions more of the tech behind the software, called Rigel. That led me to the website of ECRI, the company that makes Rigel. More good tech there."

Comments

saw this on TLC

[twiggy]

There was a great special on this software on TLC not that long ago. Basically, they were able to calculate the odds of the suspect living and/or acting in a certain area based on where the crimes were, etc.

They ended up catching the killer, and he was a cop!

From discussions I'm seeing about these shootings, it may very well be a cop or someone in the armed forces. The ballistics of the gun/ammo being used just don't fit right since people are saying they don't hear the shots, or don't hear very loud shots, so people are theorizing that there's special subsonic rounds being used to minimize noise - not easy to find with these types of bullets, from what I gather.. But I dont' know a lot about guns, so.. yeah...

Anyhow if I remember the name of the TLC special I'll post it here, it was on recently enough that it will probably be on again soon.

Re:saw this on TLC

[Happy go Lucky]

From discussions I'm seeing about these shootings, it may very well be a cop or someone in the armed forces. The ballistics of the gun/ammo being used just don't fit right since people are saying they don't hear the shots, or don't hear very loud shots, so people are theorizing that there's special subsonic rounds being used to minimize noise - not easy to find with these types of bullets, from what I gather..

Easy enough to make, though. It's not uncommon for hunters or competitive shooters to load their own ammunition at home. To make a slower bullet, just use less powder. (Okay, it's a tiny bit more complex than that, but you see the general idea.)

Also, it's not hard to mistake the sound of a gunshot for something else, and especially not in an urban area. A month or so ago, I took a complaint of a guy whose truck had been shot. With some sort of .30-caliber solid-construction bullet, original weight above 200 grains, and probably faster than 2700 feet per second from the muzzle based upon the deformation. If you don't know what that means, that's a damn loud round. I try and shoot an elk with a round like that every year, and thank god for Peltor earmuffs. Anyway, almost nobody in the neighborhood remembers a gunshot. However, everybody remembers a car backfiring fairly loudly. Coincidence? Maybe, but I don't believe in them.

So, you see where I'm going with this? It's easy to mistake the sound of a gunshot for something else if you don't know much about them. I'm going to take a stab in the dark and guess that people in an area where private firearm ownership is almost nonexistant (like much of the DC area) may not know what they did or didn't hear.

Ruining the Model

[Anonymous Coward]

Doesn't awareness of the geoprofiling model by the suspect make the model less accurate, or is there something built into it that takes this into account?

Will it work when everybody knows...

[f97tosc]

Clearly the principles of the software are very sound - and the product has been used successfully in the past.

However, now media is writing extensively about the software and the algorithms involved. A shrewd killer could use such information. He could think again about where to act, perhaps selecting sites at random, or selectively so that they would mislead the program.

Tor

Re: Will it work when everybody knows...

[f97tosc]

I think picking random sites would actually provide more information

Randomness is the opposite of information. If the sites are truly selected at random, then nothing can be infered from it (other than possibly that the killer is using a randomizing algorithm).

Of course, if the algorithm is 'a random place within 10 miles of my house', then it does not work, because then the locations are not very random.

Tor

But how good is it?

[Luddite Slayer]

Geo-profilers claim their methods have helped detectives solve about half of the 450

How many of those would have been solved without the program? I'd like to see a head-to-head, although I assume most police forces don't have the manpower to devote 2 seperate teams to the same crimes.

But what if the sniper has the software too?

[Anonymous Coward]

Could he profile himself and then know where NOT to go to find his next victims?

Re:When I go nuts, my perl script will foil them

[f97tosc]

Even if the serial killers are rational enough to change their patterns, it is still (at least) a small win for the police. The killers will have to go outside their comfort zones, into areas with which they are less familiar and/or require more travel.

Tor

Re:Sound cool but

[UniverseIsADoughnut]

problem is true random ness is not possable. He/she could be following a pattern without being aware of it. And if the sniper is trying to be random probably in doing so is causing a pattern. Humans are way to predictable over a period of time.

pretty much any random way you could come up with of doing what he is doing could leave a pattern that someone would see.

though with that said even when you have a pattern going it's still really hard to refine to being able to knock on his door or no his next move.

Hmmm, maybe it was seeing Red Dragon

[sielwolf]

But I've been thinking of Lecter's advice to Clarice in Silence of the Lambs: this looks a little too random.

Ever since I first saw the movie I've always wondered how often that is the case: serial criminals who commit the first crime locally, realize it, and then make a point of trying to be "random".

This entire scenario it doesn't look like the case: the first and fifth shooting were very close together and the entire field of action seems to be very localized. But still these sort of things always make me think of that quote. Guess because it was so imporant in the movie.

Highly trained... (my guess)

[ClickWir]

Well from what I've seen on the news and from logical conclusions... this person seems to someone that is highly trained with a sniper rifle. Most shots have been between 100 and 225 yards. I, could not get clean shots at that range. I'd be lucky to at least hit something the size of a human at that range. Something tells me that this person(s) is/are probably good at hiding and/or not being seen. Also probably good at covering their tracks.

My guess would be someone trained by military (army, marines, cia, kgb, swat, US government, maybe foreign govt.. etc.) or someone that's see WAY too many movies.

sniper anagrams

[recalci]

The DC sniper left a "Death" tarot card with the words:

"Dear Policeman, I am God"

written on it.

Some anagrams for "dear policeman i am god"

go and implode America
Laden doom pig America
impaled good American
magic doomed airplane
megalomaniac drop die
an imperial dogma code
good, an epidemic alarm

Some anagrams for "dear policeman i am god death"

imperial hated and good came
imperial death and good came
I'm a degraded emotional chap
I'm delegated macho paranoid
homicidal dead eager top man
Peter, a homicidal dead man go
dead homicidal game not rape

Re:This is scary

[lux55]

Applying purchasing patterns of average citizens (the only thing I can think of that a corporation would want to do with this idea) would reveal nothing new. For example, meet Joe.

Joe is a 35 year old male with a wife and a 3 year old son. Once or twice a week, Joe goes out to a restaurant near his work for lunch with a couple work acquaintances. Joe has been tasked with the weekly job (done on Thursdays) of doing the family grocery shopping. Joe pays their bills on the 27th of every month. He fills up with gas and buys a pack of smokes X times throughout the week on his way to or from work. Occasionally, maybe twice a month, Joe also stops to pick up a case of beer. At the same time (roughtly) every year, he goes out and buys another present for his wife because it's her birthday. He does the same for his son. He does this again predictably (which would only have been discovered through the use of patented software) the week before Christmas, at the reminder of his wife. Joe and his family go on vacation every year to the same place, because Joe's wife has family there. All of this, except the vacation, happens within a 1km radius from either Joe's home or his work.

"No alarms and no suprises..." (Radiohead for the uninformed)

Joe's probably not that far from 95% of people either. There's no holy grail of purchasing patterns to be discovered that would increase Walmart's revenues by another 100%. The funny part is that Walmart and all the boys will still try to license this technology to have this fact pointed out to them once again, and just for the fun of it since they can.

This doesn't scare me much at all. I'm a law-bidding citizen on one hand with nothing to fear, and I'm also a privacy/indie/free speech zealot as well, but I don't think this is quite the technology that will put automatic identity checks in the doorways of retail stores, or that will improperly accuse me of some heinous crime. Now required ID cards and all this DMCA garbage, that's another story.

You mean Mini14

[Wee]

That's a real small bullet, about as big as a .22 we all grew up with. In order for it to be lethal, it needs to be shot at about 1000 mps (Mach 3 ish).

For anyone curious, the .223 is about the same diameter as a .22 LR, but there the similarity ends. The .223 weighs in between 50 and 64 grains and travels at 2700-3300 fps. I think the .223 NATO round is 55 grains and moves at like 3100 fps. A .22 LR is 40 grains and travels at around 1050 fps. I might be a little off in my numbers, so don't quote me. The two are night and day as far as lethality and ballistics go, however.

It's probably a disaffected, over intellectual loner in high school or college with an M-14 or a bolt action .223 hunting rifle with a scope, who's taking out his feeling of inadequacy and powerlessness against random people. Needless to say, he's never been laid, either.

The M14 is .308, not .223. You mean a Mini14.

But I get your point. Feet first into the mulcher is too good a fate for this ass clown. Shooting old men and children and women. In the back. I'm having a hard time coming up with suitable retribution...

-B

Re: You mean Mini14

[Black Parrot]

> Feet first into the mulcher is too good a fate for this ass clown. Shooting old men and children and women. In the back. I'm having a hard time coming up with suitable retribution...

I'd go for ordinary imprisonment. Sure, this and lots of other crimes merit worse, but unfortunately our "justice" system is actually a "conviction" system, and doesn't appear to be batting too high an average on hanging the right guy.

Re:You mean Mini14

[Hieronymous Cowherd]

Actually, yes, they are, by those of us who shoot competitively. The silly '92 gun ban made several inexpensive rifles used to get started in competitive shooting into high-priced collectors' items.

Please define "high powered sniper rifle". Differentiate from "hunting rifle" or "varmint rifle" or "target shooting rifle". Please be very specific.

If you've noticed how badly-written laws about technology are, they've got nothing on the labyrinthine morass of laws that cover firearms ownership.

Re:You mean Mini14

[EricTheMad]

I think the .223 NATO round is 55 grains and moves at like 3100 fps. That's the old round. The one that is currently in use is 62 grains. The 55 grain round spins when it enters the target. This increases the lethality of the round. The 7 grain increase was made to cut down on the spin. The idea being to wound the target instead of kill. While at first glance it may seem like a bad idea, it actually makes a lot of sense. It is, as Baldric would say, "a cunning plan". The theory behind it is this: If you kill the target, you've removed one soldier from the battle. But if you only wound your target, you've taken at least two people out of the battle. Your target and his buddy, who now has to take care of him.

Re:You mean Mini14

[Twirlip of the Mists]

why is it worse to shoot "old men and women and children" than it is to shoot anyone else?

That's a good point, but the fact seems to be that our culture-- maybe all cultures for all I know-- places a higher value on the lives of the very young, the very old, and women than on the lives of adult men.

But you're absolutely right. From a thousand feet away and on the wrong side of a rifle barrel, a 35-year-old white man is just as defenseless as anybody else.

Re:You mean Mini14

[Hobophile]

That's a good point, but the fact seems to be that our culture-- maybe all cultures for all I know-- places a higher value on the lives of the very young, the very old, and women than on the lives of adult men.

I respectfully disagree with your assertion that our culture (in particular) places a higher value on the lives of the very old than on regular adults. I would say that American society in particular reveres youth and the image thereof. Further I would assert that this is true of most any Western culture, where innovation (the province of the young) is more highly thought of than tradition.

Chinese culture is an interesting exception, owing to the long tradition of Confucianism and ancestor worship there. However, my general impression -- admittedly conveyed through academia and personal intuition rather than firsthand experiences in China -- is that this has changed and continues to change as China embraces more Western ideals. Likely this holds for 'official' idealogy, though what the millions and millions of uneducated peasants in the Chinese countryside believe may be substantially different.

I think that the disgust most people feel towards those who victimize the elderly and the very young is due to how they are perceived as defenseless and worthy of sympathy/pity/protection. Note that this has little to do with the specifics of the situation -- as you correctly point out, everyone is equally defenseless from hundreds of feet away -- but simply with perceptions.

Going on purely visceral reactions, I would say that most people would consider someone who slaughtered a bus filled with schoolchildren or retired folks more despicable and abominable than someone who simply killed everyone on standard commuter bus. This would be true even if the retired folks bus was filled with ex-Navy Seals and the commuter bus filled with overweight, out-of-shape middle aged Americans.

Perhaps the key is that children and the elderly are perceived more as offenseless than defenseless -- meaning they have either done nothing that remotely merited being targetted, or did so such a long time ago that it can no longer be held against them.

Re:You mean Mini14

[Anonymous Coward]

> Easy. A "sniper rifle" is a rifle that has been used to kill somebody from a distance.

Uh, what do you mean by "from a distance"? By your rule, 2 feet is enough. What if I just smack you to death with a rifle? It's automatically a sniper rifle?

Kim Rossmo

[Anonymous Coward]

Kim Rossmo was also one of the first to suggest vancouver had a serial killer [robert pickton,pig farmer],which the VPD dissmissed promptly.The VPD also drummed Rossmo out via the old boys network because of interdept politics/powerplays.

Some background on this guy....

[puppetman]

I live in Vancouver, where Kim Rossmo got his Ph.d and started his geoprofiling.

He was very successful, and it led to his rapid advancement in the Vancouver Police Department. But like most police departments, it's still old-boys, and alot of them resented an educated individual rising through the ranks so quickly.

Finally, they told him they weren't extending his contract when he was promoted too far. He sued. During the trial, the senior VPD members were made to look like fools for lying under oath.

One of the interesting things that came out was that he suspected (back in June, 2001) that a serial killer was involved in the disappearance of 20 to 30 Vancouver women. Well, he was right. The Vancouver police are conducting a huge investigation at a pig farm in the Vancouver area, and Robert William Pickton is now Canada's most prolific known serial killer with 16 or so charges in the works, and more pending as they find more DNA at the farm.

I don't know much about the technology (or psychology) involved, but I do know that when he applied his software to some of Canada's other serial killers (Paul Bernardo, Cliffard Olsen, etc) his software picked a 4-block area which included the killer's home. It was also used to catch a killer in Abbotsford.

Thanks to a bunch of fat old men who's ego has extended past their intelligence, Vancouver has lost what appears to be a top-rate talent.

How this thing works - an explanation

[Anonymous Coward]

How does this work?

Alittle bit about geographic profiling works. Essentially, what this software does is it assigns a weight to different attributes of a crime and based upon past crimes determines a probability that the crime was commited near someone's home or an area they know. Throwing in some additional variables such as where an individual works, what route they probably take to work, etc, helps identify a person's individual daily path.

Throw in a couple more factors like how far most criminals go from home to comit a crime - i.e. bank robberies tend to happen at banks individuals don't know, further from home, though rapes and murders happen in areas people are more comfortable - near an area they know - so that if discovered they know where to run (read: no unexpected dead end roads, good alleyways etc). Without getting into the whole theory of why this is - basically its because someone near their home doesn't stand out, they've probably been seen on the street before, maybe a neighbor knows them, they dont pose a threat - and dont' look out of place. Think about yourself - if you had to go walking around alleyways to stake out a location to dump a body or commit a rape, would you feel more comfortable (and look less shady) in an area you know, or some place out of town?

So take some basic variables - what was the crime? when was the crime?

Now, take the location of your crimes and cross-reference it with just the areas that would match given crimes. You end up with an area of probability that usually circular in nature around each crime... as these areas intersect, you get "blotches" of red, yellow, orange, etc..

That done, start to take other factors into consideration. You probably don't have a database with everyone's job, route to work, schedule, etc - what you probably do have is income ranges and general demographic information for specific areas. (Ok so I mentioned all this stuff about individuals above, I'm getting there).

Using that data, you can modify the predictions futher. For example, something like a string of gang shootings... There are several areas (chicago for one, im sure you can think of one near you) that have affluent or up-and-coming areas near or next to ghettos. For chicagoans, think near west side vs. cabrini greens. For those who don't know, 2 bd 2ba condos in near west side go for about $300,000 to $500,000. Go about five or six blocks down the road though and you'll run into section-8 housing. I'm getting to a point here, bear with me.

Having run your first analysis, you may find that there was a gang shooting in the "nicer" area, but it isn't really likely the shooter is from there... more likely than not, he's from the crummier side a few blocks away. Up to this point, the system knows nothing about Street Y vs Street X. Street Y might be a few blocks from Street X, but STreet Y might be primarily a six figure area... This information exists - if not directly, it can be found through housing prices and general crime level.

Ok, so now what? We have a big red blob that winds around. Feed the system the data on population type, ethnicity (yup. Not too PC, but its there), income, average age... etc. With this new info, it starts to eliminate or decrease the red areas, building a smaller search section.

Now I'd talked about all those individual factors - I'm finally getting to them. Remember those? Where does person A work? Person B?
What does this person do? (Truckers and transients dump bodies far away, most employeed people dump them near work or home) .... etc.

Usually in cases like these you have hundreds of leads. Everyone is followed up - some are easy to eliminate some don't really lead anywhere. Some sound like good potentials. Say you get a tip that joe shmoe did this crime. A quick check reveals he has no alibi for the time in question... does he fit the (geographic) profile?

Obviously, you are going to go see joe shmoe. You ask some pretty basic questions that sound pretty boring... where do you work? You drive to work? Take the bus? What time do you leave? Do you eat lunch at work or outside? Simple stuff. You bring it up in conversation like nothing was - and for the most part it isn't anything.

Pretty soon, you've got a list of 50 individuals who could all be involved. None of them have alibis, and you need to figure out who to focus on. Here we go again.

Your now narrowed red area can take into account what these people do, where they work, how do they get to work, etc. Put those in and usually, you end up with 10 individuals who fit the geographic pattern. Those are the ones you go see again. And again.

The rest? They don't fall off the radar, but you are no longer dedicating half your team to them. It's a game of probabilities. Now with your 10 "likelies", you've got the resources pointed in the right direction.

Combine this with an FBI Profile of an individual and you've taken your 10 and shaved off 3 or 4. Now, you've got a handful of people to really focus on. At this point, you've got your search warrant if you want it - no alibi, meets the profile, fits the area, etc.

The search warrants usually lead to a few more clues and narrow it down to one guy. Then you just got to figure out how to prove it was him. :)

Re:Sound cool but

[ReconRich]

what if the guy your trying to track is a complete nutcase
Well, I'd say he's certainly some kind of nutcase. Examination of his method, however, reveals a few interesting things. First, he acts like a military sniper; that is he selects a target, takes 1 shot, and then (presumably) leaves his position, taking everything (like shell casings) with him. In other words, all the work is in preparing his site, and leaving it. The actual shooting doesn't take much time or effort. Second is his selection of target. It appears to be random, although shooting a kid going to school could be designed to cause fear. Its almost as if the target is secondary to the location; this nutball may be picking sites from which he thinks he can get someone, and then killing whoever shows up. If this is the case, this location software may be just the thing; on the other hand, his criteria for picking a site might not have anything to do with where he lives. Anyway, I hope they catch this bastard soon, and I really don't care how they do it.
-- Rich

I'd like to point out...

[Heynow21]

Police organizations also regularly hire psychics and check out their "revelations" on cases that go cold. I'm also kind of dubious about psychological profiling, but what do I know.

Re:Reaching, aren't we?

[Anonymous Coward]

Sometimes a nutjob is just a nutjob.

I should know, I'm a psychologist.

On the other hand, nutjobs do funny things like leave anagrams for us to figure out.

Being a nutjob, after all, means doing something "just a wee bit far fetched."

This guy does apparently have the sort of profile that might involve playing games with the authorities. It becomes especially realistic when you consider that he's not just killing with a butcher knife, but using a weapon of some sophistication, with some skill. He may be predatory and inhumane, but--as unfortunate as it is--he's no dummy.

You're probably right, but the possibility pointed out by the original post is interesting nonetheless. And a very real possibility.

Re:This is scary

[sbonds]

Speaking of crime data in GIS, it worth a look at your local police department to see what sorts of interesting things they have available in this area. I was surprised to find quite good GIS-based crime info for the Portland, Oregon area:

Top level link: http://www.portlandpolicebureau.com/crimemapper.ht ml

Top level map

Monster direct link to Portland downtown wide-scale crime map:

detailed downtown Portland crime info showing the locations of individual crimes.

If I was an investigator....

[mao che minh]

...I would select 10 of the USMC's and Army's best snipers, give them intel of the area, and let them hunt the sniper down. Skilled and experienced snipers should theorectically be able to deduce the most favorable target locations - geography-wise any ways. You let these 10 snipers scope out the most favorable areas in the DC and Maryland area and camp them.

Bzzzt! So sorry, let's meet our next contestant...

[PizzaFace]

OK, so I'm a sucker for an AC Troll, but I have to reply:

I live near these shootings. As I type, I hear a police helicopter overhead. My kids complain about not having outdoor recess at school. When I run an errand, I scan the perimeter of the parking lot before getting out of the car, and then jog to the door. But at least I'm not paranoid!

It's not a government plot to stir up anti-Iraq rage because (1) these daylight suburban shootings are too risky for a plot that would need to avoid detection at all costs; (2) the public has had no reason to think that the sniper attacks are related to terrorism, let alone to Iraq (unlike the anthrax attacks of last winter, which apparently were the work of a right-wing kook who wanted to look like an axis-of-evil terrorist); (3) the government has evil elements, but not THAT evil - not hunting rifles against children.

Until less than 24 hours ago, I thought the sniper was probably an Al Qaeda terrorist. No, he hadn't made political demands, but neither did the September 11 hijackers. Far from causing me to favor war against Iraq, though, the prospect of terrorism reminded me that we'll face much more of it if we continue to make war in the Middle East (for no very good reason).

Anyway, the tarot card seems to dispose of my terrorism theory, as well as your government-plot-posing-as-terrorism theory.

"Mapping Crime", et al - FREE NIJ research reports

[ivi]

Research Report, Mapping Crime: Principle and
Practice by Keith Harries Ph.D. December 1999:

www.ojp.usdoj.gov/nij/pubs-sum/178919.htm

('lots of other research reports are there for
cost-free downloading, too; including one into
RH Linux 7.1's GNU dd as a disk imaging tool.)

Re:This is scary

[MartinB]

Shows what you know. The following is based on real analysis, carried out in the UK by a major supermarket.

Basket analysis shows that for stores in Joe's area, there's a certain tendency for people to buy beer and nappies (diapers) together. This sparks some qualitative research, and they discover that it's largely because of men sent out to buy nappies also buy beer to reward themselves.

So as an experiment, the supermarket's store manager places some high-profit brands of nappies next to the beer section. Sales go up, and not only that, more profitable sales go up. Store manager gets a big bonus.

Next, the supermarket expands the test to neighbourhoods of similar socio-demographic profile to the first one. Sales of high-profit brands go up nationwide, because retail behaviour has a strong correlation to socio-demographic profile. That's the GIS bit - which doesn't actually need tying into individual consumers.

Even if total sales of nappies don't increase, the sales of specific brands does. This gives the supermarket leverage with nappy manufacturers to extract fees for putting their brands next to the beer section. (Incidentally, many manufacturers don't know exactly how much they're shelling out in promotional costs... which can lead to big holes in their account - as happened to Bulmers recently - 3m+ spent without anyone noticing)

So while total sales doesn't change, profit does, because there's additional profit from the high-margin brands, and additional shelving fees from the manufacturers.

And that's just one category... most supermarkets have several thousand categories. Profit doesn't have to increase 100% year on year - double digit is fine, especially in the current climate.