Forgot your password?
typodupeerror
Software Your Rights Online

Software Used To Predict Who Might Kill 361

Posted by kdawson
from the three-psychics-in-a-pool dept.
eldavojohn writes "Richard Berk, a University of Pennsylvania criminologist, has worked with authorities to develop a software tool that predicts who will commit homicide. I could not find any papers published on this topic by Berk, nor any site stating what specific Bayesian / decision tree algorithm / neural net is being implemented." From the article: "The tool works by plugging 30 to 40 variables into a computerized checklist, which in turn produces a score associated with future lethality. 'You can imagine the indicators that might incline someone toward violence: youth; having committed a serious crime at an early age; being a man rather than a woman, and so on. Each, by itself, probably isn't going to make a person pull the trigger. But put them all together and you've got a perfect storm of forces for violence,' Berk said. Asked which, if any, indicators stood out as reliable predicators of homicide, Berk pointed to one in particular: youthful exposure to violence." The software is to enter clinical trials next spring in the Philadelphia probation department. Its intent is to serve as a kind of triage: to let probation caseworkers concentrate most of their effort on the former offenders most likely to be most dangerous.
This discussion has been archived. No new comments can be posted.

Software Used To Predict Who Might Kill

Comments Filter:
  • popcorn (Score:3, Funny)

    by Anonymous Coward on Monday December 04, 2006 @03:14AM (#17096362)
    Hey I've seen that movie! Tom Cruise survives and gets to have the cute girl!
  • by macadamia_harold (947445) on Monday December 04, 2006 @03:14AM (#17096364) Homepage
    I could not find any papers published on this topic by Berk, nor any site stating what specific Bayesian / decision tree algorithm / neural net is being implemented.

    Yeah, I think if you ask for it to answer that question, the algorithm responds "I'm sorry dave, I'm afraid I can't do that."
    • He is probably just using an SPR (statistical prediction rule), so his program is probably 1 line long, and the real work went into mining the data to determine what the rule should be.
  • Reference (Score:5, Informative)

    by Quixote (154172) * on Monday December 04, 2006 @03:16AM (#17096376) Homepage Journal
    This paper was published in the June 2006 issue of "The Journal of Quantitative Criminology".
    Here are the pertinent details:
    Title: Forecasting Dangerous Inmate Misconduct: An Application of Ensemble Statistical Procedures
    Journal: Journal of Quantitative Criminology
    Issue: Volume 22, Number 2 / June, 2006
    Pages: 131-145

    Abstract:
    In this paper, we attempt to forecast which prison inmates are likely to engage in very serious misconduct while incarcerated. Such misconduct would usually be a major felony if committed outside of prison: drug trafficking, assault, rape, attempted murder and other crimes. The binary response variable is problematic because it is highly unbalanced. Using data from nearly 10,000 inmates held in facilities operated by the California Department of Corrections, we show that several popular classification procedures do no better than the marginal distribution unless the data are weighted in a fashion that compensates for the lack of balance. Then, random forests performs reasonably well, and better than CART or logistic regression. Although less than 3% of the inmates studied over 24 months were reported for very serious misconduct, we are able to correctly forecast such behavior about half the time.

    Unfortunately, you've got to pay $30 to get this paper. Maybe some slashdotter with a school/corp subscription to Springer will put up the text? ;-)

    • Re:Reference (Score:4, Informative)

      by Anonymous Coward on Monday December 04, 2006 @03:26AM (#17096424)
      • Re:Reference (Score:5, Informative)

        by dch24 (904899) on Monday December 04, 2006 @03:45AM (#17096542) Journal
        Thanks! However, reading the paper, it seems that this paper is about the California Department of Corrections, and is not actually about who will commit homicide "on the outside." It's about which prisoners are "likely to engage in serious misconduct while incarcerated" (from the abstract). I don't know if this is the right paper. In fact, I'm going to guess that Berk hasn't published a paper on his new method. This paper may be a similar method, but there's no way to know that.

        I also wonder in yousendit.com can handle a slashdotting. I guess we'll know soon!
        • by dysk (621566)
          I also wonder in yousendit.com can handle a slashdotting. I guess we'll know soon!
          On the link I posted below I've only gotten 50 hits, and yousendit has a limit of 100 downloads for unpaid accounts, so I don't think too many people are clicking on the article.
    • Re:Reference (Score:5, Informative)

      by dysk (621566) on Monday December 04, 2006 @03:37AM (#17096490)
      Interesting stuff. Here's a link to the full text:

      http://130.58.240.179:8080/~erek/minorityreport.pd f [130.58.240.179]
    • by QuantumG (50515) *
      Dear god why. You've read the abstract, it's no better than guessing.
  • by Rix (54095) on Monday December 04, 2006 @03:17AM (#17096378)
    Their probation officer pays more attention to them, and they feel trapped in the system. They can't move on and contribute positively, and lash out violently.

    Thanks, that helps.
  • Utter BS (Score:2, Insightful)

    by suv4x4 (956391)
    "Richard Berk, a University of Pennsylvania criminologist, has worked with authorities to develop a software tool that predicts who will commit homicide.

    This is utter BS, and a plain simple statistics based profiler.
    I'm so pissed off after reading about this "supposed", that I wanna kill someone.

    And don't forget, all arabs are terrorists! Don't forget to give them obvious, dirty looks full of awareness of their terroristic descent, when you happen to see one.
    • Probably does more then statistics. Reminds me of a story.

      This girl and her sister are attending a funeral of their mother who has died of old age. At the funeral the girl meets this guy she never met before, both hit it off big time. However when she gets home she realises that she got no contact information so is unable to speak to him. A few days later the sister is murdered by the girl. Why?

      • by suv4x4 (956391)
        This girl and her sister are attending a funeral of their mother who has died of old age. At the funeral the girl meets this guy she never met before, both hit it off big time. However when she gets home she realises that she got no contact information so is unable to speak to him. A few days later the sister is murdered by the girl. Why?

        I'll tell you if you guess my age which is three times what it was X years ago and 5 times it was Y years ago, and somehow manages to be a prime number, and contain square
      • by suv4x4 (956391)
        This girl and her sister are attending a funeral of their mother who has died of old age. At the funeral the girl meets this guy she never met before, both hit it off big time. However when she gets home she realises that she got no contact information so is unable to speak to him. A few days later the sister is murdered by the girl. Why?

        BTW, if this was The Real World, I wouldn't really suspect she did it to meet the guy at the funeral, but because her mother left everything to her sister, and the guy has
      • Re: (Score:2, Interesting)

        by Petersson (636253)
        This girl and her sister are attending a funeral of their mother who has died of old age. At the funeral the girl meets this guy she never met before, both hit it off big time. However when she gets home she realises that she got no contact information so is unable to speak to him. A few days later the sister is murdered by the girl. Why?

        Hey, that's a psychological classics. If the reply is 'I have no idea, there must be something missing in the story' the person asked have thinking homicidal deviations.

        • Re: (Score:3, Insightful)

          by suv4x4 (956391)
          Hey, that's a psychological classics. If the reply is 'I have no idea, there must be something missing in the story' the person asked have thinking homicidal deviations.

          However if the first thing that comes to her/his mind is 'It's clear, she killed her sister in order to be at another funeral so she could meet the guy again' then there is higher possibility that there could be something wrong with the asked person.


          Wait, both answers demonstrate "thinking homicidal deviations", so what is the answer that me
          • by DarkSarin (651985)
            Fortunately, most of the real psych out there isn't as looney as the pop-psych stuff like this. Note I said most. There are still a few moonbats, but most are safely hidden away where they can't do much real damage.

            (Pet psychology indeed! Don't get me started!)

            (Oh, did I mention that I am in an Applied Psych PhD program? Yeah, well, okay, now I have, but I still like what my dad told me when I asked him why he switched majors away from psych-"Too many cooks" (as in loonies!).)
      • Don't leave me hanging...does this have a "right" answer?

        Is this the ole' "do you resent the accusation, or assess the evidence against you" trick question? I.e. Did you kill your cousin?

        Innocent response: what the hell is the matter with you?

        Guilty response: what makes you think I did?
        • > Don't leave me hanging...does this have a "right" answer?

          No right answer, 1 wrong answer. :) Answered in the other replies.
        • by suv4x4 (956391)
          Is this the ole' "do you resent the accusation, or assess the evidence against you" trick question?

          [Person1:] I.e. Did you kill your cousin?


          [Person2:] But he's alive...

          [Person1:] Oh.. well then.. Hmmmmm..... Wanna go for a drink in the pub nearby?

          [Person2:] Sure.

          [Person1:] Did you kill your mom?

          [Person2:] Dude, something's definitely wrong with you, I tell ya.
        • by tomjen (839882)
          do you resent the accusation, or assess the evidence against you

          I will go fetch a dictionary
      • Clearly, the girl was on fire.
    • That was my first thought on this article as well, until I read the last line: "to let probation caseworkers concentrate most of their effort on the former offenders most likely to be most dangerous."

      If this is only used in that manner, then it seems like a good idea to me. However, that's a huge if, and I don't believe for a second that it will only be used by probation officers against convicted criminals.
      • Re:Utter BS (Score:5, Informative)

        by Llywelyn (531070) on Monday December 04, 2006 @04:26AM (#17096714) Homepage
        1) Convicted criminals are the only ones that concern probation officers.

        2) Convicted criminals are the only ones they are likely to have the data to fill most of the fields for.

        3) Probation officers have a job to do that does not involve tracking random citizens.

        Thus, it seems unlikely it could be used for anything *but* the intended purpose without a fairly serious rework.
        • Initially, I wasn't thinking about tracking random citizens as much as I was thinking about it being used during sentencing. I can just picture a first time assault offender having this used against him to send him to jail because "he is likely to do it again". I can't give an in depth example of how that would work and IANAL, but I've read about enough obscure cases to know that some lawyers are good at their jobs and can do things that I wouldn't ever think would fly.

          In another example, picture a viole
      • by mgblst (80109)
        That was my first thought on this article as well, until I read the last line: "to let probation caseworkers concentrate most of their effort on the former offenders most likely to be most dangerous."

        If this is only used in that manner, then it seems like a good idea to me. However, that's a huge if, and I don't believe for a second that it will only be used by probation officers against convicted criminals.


        Sure, everything is presented in a good light, to get funding. The A bomb was written as a w
    • by Mr2cents (323101)

      And don't forget, all arabs are terrorists! Don't forget to give them obvious, dirty looks full of awareness of their terroristic descent, when you happen to see one.
      Is it hate week already? Great!
    • Not Utter BS (Score:2, Insightful)

      by Dragon Bait (997809)

      And don't forget, all arabs are terrorists! Don't forget to give them obvious, dirty looks full of awareness of their terroristic descent, when you happen to see one.

      There are scientific reasons behind human behavior. Elevated testosterone will tend to elevate violent behavior. Raised in an abusive home raises the likelihood of being an abuser. Raised in a racist home raises the likelihood of violence against other races. Raised with a religion of violence, one is more likely to be violent.

      Given eno

  • A bit uneasy? (Score:5, Insightful)

    by sqrt(2) (786011) on Monday December 04, 2006 @03:23AM (#17096410) Journal
    This sounds like a really BAD idea to me. Either it works really well and then people will start asking why it isn't being used on the general population or it wont work and we'll be focusing our attention on the wrong people. What's the indicator of success? A reduction in homicide rates among people singled out? Our justice system is based on dealing with people AFTER they break the law, everyone, even people at "high risk" to commit crime have to actually do something wrong before you can take action. It may just be used to focus rehabilitation and surveillance efforts on high risk people, but the profiling potential for this must be obvious to the people who designed it, then all it takes is for a little public exposure of how this system could have saved some children if it had been used more aggressively. I'm a bit uneasy about any technology or system that seeks to punish people retroactively. The way the article describes it as working seems harmless now, but the potential of abuse is there. Definitely something to keep an eye on.
    • It simply needs to work better than the current methods to be useful. Something to keep an eye on, but it's a lot better than racial profiling. A lot better.
  • by suv4x4 (956391) on Monday December 04, 2006 @03:29AM (#17096442)
    Excerpt from the test:

    ...

    21. Ever killed or tortured small animals?

    22. If yes, did you often think they enjoyed it and wanted more?

    23. Are you a minority?

    24. Do you read Slashdot?

    25. Regularly?


    26. Would you punch a guy with glasses in the face?

    27. Would you punch a clown in the balls?

    ...
  • by Salvance (1014001) * on Monday December 04, 2006 @03:33AM (#17096464) Homepage Journal
    This study was done on incarcerated criminals. Even attempting to apply the findings to people outside prisons would be a HUGE mistake. Now if they conducted a similar set of questions on a few thousand randomly selected members of the public and were able to show the same high correlations, that would be a different story entirely.
    • by Telvin_3d (855514)
      God, can you imagine the liability from that?

      "well, we were fairly sure he was going to kill someone, but if we hadn't let it happen we wouldn't know if the test was valid"

      heh
  • by 8ball629 (963244)
    I'd like to beta test this on myself ;).

    Also, how long will it be before myspace users have this survey on their webpages or is it already there?
  • Interesting (Score:2, Insightful)

    by suv4x4 (956391)
    You can imagine the indicators that might incline someone toward violence: youth; having committed a serious crime at an early age; being a man rather than a woman, and so on. Each, by itself, probably isn't going to make a person pull the trigger. But put them all together and you've got a perfect storm of forces for violence

    Is Berk implying that a checklist of questions can make someone pull the trigger?

    Well in this case I suppose we have no choice but TO KILL THOSE PEOPLE IN ADVANCE I think! Oops. Well w
  • by djupedal (584558) on Monday December 04, 2006 @03:48AM (#17096552)
    "Do you make up these questions, Mr. Holden? Or do they write 'em down for you?"

    "The tortoise lays on its back, its belly baking in the hot sun, beating its legs trying to turn itself over but it can't. Not without your help. But you're not helping."

    "WHAT DO YOU MEAN, I'M NOT HELPING?"

    "I mean you're not helping! Why is that, Leon?"
    • If the test in TFA indicated that I could murder would it at least prove that I was human?

      OTH you wouldn't want a person to sit down with a prison inmate and ask them these questions face to face, particularly if the interviewee in question had a handgun under the table, which I suppose is your point.
      • by djupedal (584558)
        "...you wouldn't want a person to sit down with a prison inmate and ask them these questions face to face"

        Inmate, machine, human, whomever - the point is, just be sure to check under the table! :)

        These types of profile-determination exams always entertain me. I was with a group of ruffians one night, minding our business as it were, when a pair of local Sheriffs came 'round to see if any of us warranted their interest. They lined all ten of us up and went down the line, one by one...

        Cop #1 to Ruff
  • So SpamAssassin works this way. Any one criteria (such as from a dynamic IP address) generally isn't enough to consider email spam. You need to have a number of factors contribute both positively and negatively to the final score, after which it's considered spam. But this is for humans. Maybe the software is called PeopleAssassin?
     
  • "70% confident this man will commit murder" = 30% are definately not murderers who will be discriminated against as being a high risk murderer.

    "95% confident this man will commit murder" = 5% are definately not murderers who will be discriminated against as being an EXTREMELY high risk murderer.

  • And yet again (Score:5, Interesting)

    by TCM (130219) on Monday December 04, 2006 @04:06AM (#17096632)
    ...the attempt to solve with technology what can't be solved by technology.

    How about having social workers that deserve that job title? Do we soon replace all judgment on humans and human interaction with computers'?

    It is this very dehumanization that causes violence among humans in the first place. How long until someone is flagged by this and it becomes a self-fulfilling prophecy because he feels trapped?

    This whole anti-social project shouldn't even have started. What a waste.
    • Re: (Score:3, Informative)

      by inviolet (797804)

      Take care to maintain context here. This project is not about individual judgments of other individuals. This project operates on the macro level, directing limited resources where they are most likely to have the greatest benefit. Only after all the likelihoods have been maximized do we re-introduce individual attention and individual treatment. (How else would you apportion too few workers to too many cases?)

      And don't worry, just because you're predictable, doesn't mean you don't have free will. You

  • has worked with authorities to develop a software tool that predicts who will commit homicide.

    Don't forget the best practices for committing a homicide:

    1. Commit often and early, to prevent victim escape.

    2. Copycat homicide is cheap, so don't be afraid to branch existing homicides, if you feel you need to.

    3. While committing a homicide, always write down a full log of what happened, and put it with it with body (or bodies). This won't just help the cops get oriented, but also to yourself when you come back
  • by robot5x (1035276) on Monday December 04, 2006 @04:15AM (#17096662)
    actually there are many tools like this already in existence... modern probation work has been scientificalised and statisticalised to the extent that you can't do anything with an offender until you know what their various scores are. In the UK the risk of general reconviction is calculated statistically in the OGRS programme based on age, conviction, prison sentences etc. (http://www.homeoffice.gov.uk/rds/probation1.html [homeoffice.gov.uk]) . This also produces a level of risk that that person will commit a violent offence. There are other specialist tools for domestic violence - the Spousal Assault Risk Assessment which is a 20 item checklist. Also, for sex offenders their risk of reconviction is assessed by using the Thornton Risk Matrix 2000. Every offender who comes into the probation system also has an OASys assessment completed on them - which asks the assessor to score factors from 14 different areas such as accommodation, lifestyle, substance misuse etc. (http://www.probation.homeoffice.gov.uk/files/pdf/ Info%20for%20sentencers%203.pdf [homeoffice.gov.uk]).
  • by Llywelyn (531070) on Monday December 04, 2006 @04:21AM (#17096682) Homepage

    "This will help stratify our caseload and target our resources to the most dangerous people," probation department director of research Ellen Kurtz said

    Emphasis added.

    This is being used by people who have already been tried, convicted, and sentenced and are being monitored and required to check in anyways. The model, further, was derived from the probation system (not from those already in jail):

    "Using probation department cases entered into the system between 2002 and 2004, Berk and his colleagues performed a two-year follow-up study - enough time, they theorized, for a person to reoffend if he was going to."

    This is just being used to help parole officers decide how to allocate their caseload. That's a Good Thing(TM). No one seems to be talking about applying it to society in a minority report fashion, and while such a harebrained scheme may eventually be table, it needs to be evaluated independently of whether it is a good idea for parole officers deciding how to allocate limited resources.

  • Something similar (Score:3, Interesting)

    by denoir (960304) on Monday December 04, 2006 @04:39AM (#17096774)
    There is a similar thing on this site [peltarion.com] showing how to predict which police cadets would become good cops and which would become bad cops. It's some form of neural net tutorial, but the conclusions are (at least to me) remarkable:

    We can with 96.55% confidence say that a graduating cadet will be failing at his job in five years and we can with 99.17% confidence say that a graduating cadet will be performing an adequate job five years in the future.
  • by goldcd (587052) on Monday December 04, 2006 @04:40AM (#17096784) Homepage
    and tried a couple of similar package before. They're all snakeoil.
    Nothing can replace years of professional practice and the ability to analyze the bumps on a perps skull.
    • Re: (Score:3, Interesting)

      by BenjyD (316700)
      I was thinking that: my gf works for the local probation service and they use a software package that gives them a risk score of some sort based on the offender's history.
    • Re: (Score:3, Funny)

      by sharkey (16670)

      analyze the bumps on a perps skull.

      He was arrested by the LAPD, huh?

  • by kan0r (805166) on Monday December 04, 2006 @04:47AM (#17096816)
    Scotland Yard agrees:

    It looks like Scotland Yard [timesonline.co.uk] is also looking for scary new tactics in fighting crime. The latest idea of Laura Richards, head of analysis of the Metropolitan Police's Homicide Prevention Unit, sounds like a strangely familiar concept to those who have seen Minority Report. She aims to create a database of people who could supposedly commit a crime in the future, based on their psychological profile.

    Even though preventing crimes is a noble motivation, this idea raises serious privacy issues.

    As a sidemark it should be mentioned that Laura Richard also seems to be part of the team that "revealed" Jack the Ripper's face some time ago.

  • They should use the predictive capability of markets instead. Set up a little in-prison pool of money on who might kill; whoever trades highest, is most likely to kill at a given moment. It'll work great !
  • So, Richard, how'd you score?
  • Typically, when you see this kind of "Behold, this will totally solve {problem X}" type project, its really just an academic trying to get national attention, so that he'll be noticed by someone running for an election at some point, and will thus get a "Vote for me, because I endorse {impossible solution that sounds good in a press byte X}" grant. Very few psychologists of any reputability put too much stock in these magical little Q and A's nowadays...
  • "concentrate most of their effort on the former offenders most likely to be most dangerous"

    So we already know which are most likely to be dangerous, and we're going to use some simplified-down-to-40-attributes computer software to.... reassure us of what we already suspected? Hmmm..
  • "Software Used To Predict Who Might Kill"... hmmm

    You know, the issue with this definition is technically anyone *MIGHT* kill.

    Now, make me a software that predicts who *WILL* kill, whom and when, and we're in business :D
  • From TFA: Asked which, if any, indicators stood out as reliable predicators of homicide, Berk pointed to one in particular: youthful exposure to violence

    Seen the news from Iraq lately?

    Looks like we're creating a whole generation of homicidal maniacs over there...
  • ... a piece of software that can predict from a 5-minute test game of Quake who's most likely to frag ?
  • I was expecting to find an online, multiple-choice questionnaire ..... "Are you a murderer?" sort of thing. What a disappointment!

    Unfortunately I have a big programming task ahead of me for today; otherwise I'd do it myself with a few lines of Perl and a MySQL database.
  • by bmo (77928) on Monday December 04, 2006 @07:02AM (#17097390)
    And I went up there, I said, "Shrink, I want to kill."

    "I mean, I wanna, I wanna kill. Kill. I wanna, I wanna see, I wanna see blood and gore and guts and veins in my teeth. Eat dead burnt bodies. I mean kill, Kill, KILL, KILL!" And I started jumpin up and down yelling, "KILL! KILL!" and he started jumpin up and down with me and we was both jumping up and down yelling, "KILL! KILL!" And the sergeant came over, pinned a medal on me, sent me down the hall and said, "You're our boy."

    --
    BMO

  • If you have the misfortune to be labeled by this method as a potential offender, there's a 10% chance that you are. That's a 90% chance that you aren't.


    On the other hand, if you're an offender, there's a 50% chance you'll be labeled. Thats a 50% chance you won't.


    Better than chance, I suppose, but a useful predictive tool it is not.

  • Software such as this is not really new. IIRC, the LAPD has been using a software called MOSAIC, made by an expert in violent behaviour, Mr. Gavin De Baker (and associates).

    http://www.mosaicsystem.com/ [mosaicsystem.com]

    The software is deployed in, for instance, a setting where a women has been battered by her husband. By feeding some data on the perpretator and the victim, the police department might recomend a women that she not return home, due to a huge statistical chance of her being murdered, according to data compounde
  • So they will adminster this early in childhood so they can weed out potential bad kids?

    "sorry, but johnny has been expelled from school beacuse he might, someday, perhaps do bad things somewhere, to someoene"

    So, without schooling and unable to find work, he falls in to the world of crime, proving the assumption that he was a bad kid afterall.
  • This is Silly (Score:3, Insightful)

    by eno2001 (527078) on Monday December 04, 2006 @12:33PM (#17100210) Homepage Journal
    I think ANYONE would kill under the right circumstances. Look at war for instance... All soldiers have to kill at one point or another during a war. Whether it's hand to hand combat, pointing a gun and firing or dropping a bomb. It's all killing. You also have crimes of passion where someone loses control and goes over the line. A parent who witnesses something horrific happening to a child will likely lash out in a rage which would certainly cause death under the right cirumstances. The same for a spouse. You can't predict who will or won't kill if you don't know the situation the person is in.
  • by Alain Williams (2972) <addw@phcomp.co.uk> on Monday December 04, 2006 @01:05PM (#17100698) Homepage
    this gets applied generally ... to work out who is going to comit some crime, why not round them up before they do it and save us all a lot of bother.

    So: what if you know that you have all the contra indicators: black male youth, poor background, divorced parents, ...

    Why bother to do anything: you can't get credit (you are going to be a criminal - right ?), you can't get to be an apprentice or into a good college (you are going to be a criminal - right ?), ...

    I can see this happening. Be scared, real scared!

  • by Quickening (15069) on Monday December 04, 2006 @01:30PM (#17101084) Homepage
    ...before he was elected. More than 750,000 people might still be alive.

We are Microsoft. Unix is irrelevant. Openness is futile. Prepare to be assimilated.

Working...