Become a fan of Slashdot on Facebook

 



Forgot your password?
typodupeerror
×
Privacy Communications Wireless Networking Hardware

Cell Phones Predict the Future 240

An anonymous reader writes "Wired News reports that cell phones were used in a recent project at MIT to both document and predict the lives of 100 MIT faculty and staff members. During the Reality Mining Project at MIT, Researcher Nathan Eagle logged 350,000 hours of data over nine months about the location, proximity, activity and communication of volunteers through cell phones carried by the participants. From the article, "Given enough data, Eagle's algorithms were able to predict what people -- especially professors and Media Lab employees -- would do next and be right up to 85 percent of the time."
This discussion has been archived. No new comments can be posted.

Cell Phones Predict the Future

Comments Filter:
  • by garcia ( 6573 ) * on Monday July 25, 2005 @01:39PM (#13158409)
    "We want to have our life choreographed, cataloged, witnessed and archived," Stakutis said. "Now we are heading to a world where this is possible without effort."

    Do we? It's one thing to have a personal diary or blog that you opt-in to submit information to daily. Hell, I have even expanded on my mobile pics [lazylightning.org] to include a "blog" of what I did during any particular day... That's my *choice* to put that information out there for people to see. It's not mandated by my cell phone to take pictures of what I'm doing and throw them into a database that I have no control over.

    While Eagle "acknowledges that the project raises some important questions about privacy and about the ownership of data, and says people should feel empowered, not scared, by his cell-phone applications," I just can't get passed his statement earlier in the article:

    The Media Lab behavior is beautifully regular, but the lab lives and dies by sponsors' meetings," Eagle said. "So the weeks leading up to sponsors' meetings, people are pulling all-nighters and people are going crazy trying to get their demo working.

    Is this another demo for one of your sponsors that might end up buying the rights of this technology from you and then creating their own spyware network of their mobile users' daily habits? Tracking when, where, and how they communicate to "better" serve them with advertisements and the selling/stealing of their data to other institutions and data thieves?

    He has already founded a company called MetroSpark that in September will launch a Bluetooth-powered social-introduction service.
    After filling out a personal profile, MetroSpark will attempt to be a gracious, ubiquitous host that connects people with common interests, whether they are technology conference goers who share an interest in motorcycles or barhopping singles who love long walks on the beach at sunset.


    Oh, so you started this company -- got it advertised on Wired and now Slashdot -- and it's never going to get bought out by someone else (i.e. Dodgeball) and they aren't going to use this huge database of customer data that was originally meant to be benign?

    I predict that even more corporations are going to have a field day with this data than what they originally intended (i.e. when/where you have your cell phone on and how many days a week you are sitting at home letting the CATV wash over you). If the corporations (and then obviously the government) can track social networks and trends via software on the phones you can bet your ass they are going to include it "free of charge" while still restricting your "free" access to any other programs you might want to run.

    I predict that people will fall for this invasion just like any other. We're seriously one step closer to the "Big Brother" that everyone used to fear... Now we are welcoming him with open arms!
    • It's not that deep (Score:2, Interesting)

      by TommyBlack ( 899306 )
      I think it's great that someone's working on this technology, and there's no reason to assume that it's going to be used for some nefarious purpose. The horrible thing about "Big Brother" wasn't that he knows what you're doing, it's that he stops you from doing what you want to do. All this privacy nonsense really has to stop. It really doesn't matter who knows what you're doing, and chances are a lot of people know a lot about you just by looking. I don't think it has any negative impact on my life if
      • by garcia ( 6573 ) *
        there's no reason to assume that it's going to be used for some nefarious purpose.

        he openly admits that there are privacy implications and that he's starting up a company (TBF it is benign right now) that's going to track social networks via mobile phones. As I stated above, that technology will likely be bought out by some corporation and used for their own records. It's not even so much the corporations or the government that worries me. It's intrusions via inappropriate third parties (ala T-mobile)
        • by Marxist Hacker 42 ( 638312 ) * <seebert42@gmail.com> on Monday July 25, 2005 @02:15PM (#13158809) Homepage Journal
          You are a direct product of this time period. "I have nothing to hide. I don't care." That's what's wrong. People *should* care and *should* be questioning that idea.

          How about preventing the social constructs that encourage such abuse instead of trying to prevent technology from advancing? The danger I see in this thread isn't from the technology- the danger comes from the fact that we've already let corporations become first class citizens- making real human beings mere second-class has beens at best. Worrying about privacy is just a symptom- the real problem is an overly invasive, super-powerfull business world that places profit above all other considerations.
        • I don't know.

          Intuitively I have an appreciation of privacy, of the fact that I very much like being able to do things which not everybody knows I'm doing, and that if I suddenly lost my privacy I would feel extraordinarily uncomfortable.

          On the other hand, I feel that "information wants to be free," and that by facilitating the spread of information we will be able to learn more things and generally improve life for everyone. Furthermore, stuff like this, the ability to proccess all that data and analyze i
          • information wants to be free

            Yes! In fact, you just know that your SSN, DLN, credit card and checking account numbers have been whispering to you, "Set us free... tell everyone about us... set us free..."

            That information wants to be free! Do it now!

      • Excellent. Step right this way, sir. We have a glass house for you to live in, complete with glass bathroom. Please ignore the people who appear to be pointing and laughing at you; they don't exist.

        For others' convenience, we have also posted your bank statements online. Several thousand financial institutions would like to send you a free brochure.

        The surprise trip you wanted to surprise your wife with -- well, too bad that it became a Slashdot poll!

        Those hateful things you said to your best friend a

    • by HTH NE1 ( 675604 ) on Monday July 25, 2005 @01:53PM (#13158574)
      "We want to have our life choreographed, cataloged, witnessed and archived," Stakutis said. "Now we are heading to a world where this is possible without effort."

      Indeed, next comes the government contract to expand and fully exploit this information. Soon, local law enforcement will be using this data to do their jobs more efficiently and stopping people for questioning just because they've "strayed from the herd".

      And they'll do it without directly violating your privacy because they won't see the data that was the basis of the alert. As long as no one but the black box doing the mining sees your private information and doesn't disclose any of it with its findings, it's not going to be seen as a violation of your privacy. Privacy violations will become defined as disclosure of one person's information to another person, and machines running automated processes will be exempt by definition.
      • Are you sure your name isn't chicken little, because it sounds like you think the sky is falling.

        Ok, so that joke isn't funny, it's a stupid troll but I think you're taking things a little too far. Could the scenerio you've depicted occur? Sure could, will it occur? In my mind, it is highly unlikely. Things are never as bad as the cynics say and never as good as the optimists believe; besides governments are becoming less and less important in the world. If anything, I see this technology being used t
        • by garcia ( 6573 ) * on Monday July 25, 2005 @02:19PM (#13158854)
          In my mind, it is highly unlikely. Things are never as bad as the cynics say and never as good as the optimists believe; besides governments are becoming less and less important in the world.

          You're 100% right, they won't enter into a contract for the data as they would have to pay for that. They will just claim it's to track a terrorist cell and take the information under the guise of National Security.

          It's far more devious this way as the American Public might never hear about it as it's illegal to announce that an investigation is happening.

          We have no longer have protections of anonymoys sources to the press, we no longer have protections of our privacy from repressive regimes, and we have people that continue to go around thinking that it is all right because "they have nothing to hide".

          Stop creating the means to make it easier for the corporations and the government to do what they have been trying to do for decades.
        • Things are never as bad as the cynics say and never as good as the optimists believe; besides governments are becoming less and less important in the world. If anything, I see this technology being used to improve targetted advertising; afterall everything in American society goes back to making dollars. Having a police force keeping people "in line" would be a waste of money.

          That thought is analogous to the thought of security through obsecurity. Your line of reasoning is that it is not dangerous sim

        • Head shots are now a standard police tactic in London, I wouldn't put this past governments.
    • What's this? Decrying a new technology based on its potential applications? Am I reading the same Slashdot that I used to? Everything has the potential for abuse. Does this mean we should stop developing new uses for networks?

      This service appears to be 100% opt-in. Therefore, those who choose not to use it (like me and, I assume, you) will never be affected by it.
    • Why data thieves? Our dear government would love it even more. Department of Fatherland Security would definitely use it. When you do what it predicts you are OK, but if you deviate, they will be sending the Man In Black (FBI). The study clearly shows that 15% of the time all MIT professors are terrorists...
  • by toucci ( 834101 ) * on Monday July 25, 2005 @01:39PM (#13158410) Journal
    Now, let's use this technology for cell phone highway safety:
    85% chance of obstructing traffic
    40% chance of unwittingly drifting into your lane
    0.2% chance of hitting the center divide.

    I'd wager those numbers are spot-on.
  • by metlin ( 258108 ) * on Monday July 25, 2005 @01:39PM (#13158412) Journal
    Hmm, not entirely the same thing, but I'd worked on a project called ScheduleNanny, where we used people's PDAs coupled with GPSes to predict where they will be.

    There were some interesting emergent behaviors - for instance, the system would know that I have to go to the bank later in the day and I would drive by the bank in the morning, so it would indicate that I could save time by going to the bank then. Or for instance, it would beep in the morning that it was time for me to go shower or go to the train station.

    Details can be found here [metlin.org].

    All in all, it was pretty good - after some amount of initial bootload information, you can take away the GPS and quite accurately predict where people are likely to be. This looks fairly similar, in some ways.
    • by op12 ( 830015 ) on Monday July 25, 2005 @01:57PM (#13158620) Homepage
      *Beep* It's been a month since you showered and stepped out of the house! *Beep*
      • Thanks for the laugh! Where are those modpoints when I need em.
      • Well, regularity and frequency are essential for it to beep - so, if I didn't shower regularly or frequently, it would not beep.

        Actually, what would happen is that the GPS would pick up the signal only if it's near a window - so, the bedroom or the bathroom were the only two locations where it could pick up the locations.

        We decided to test it for localization at a granular level and so, I'd take it every morning when I wake up to the bathroom. Consequently, it actually thought that the bathroom was a diff
    • Or for instance, it would beep in the morning that it was time for me to go shower or go to the train station.

      Ummm, not to focus on this one point, but do people with friggin' PDAs actually tell the damned thing to beep when it's time to shower?????

      As a non-user of PDAs or any formalized scheduling method whatsoever, I'm simply shocked that the routine things like bathing and grooming get scheduled by people.

      Then again, that's why I'll probably never be in the market for a PDA.

  • by mrRay720 ( 874710 ) on Monday July 25, 2005 @01:39PM (#13158413)
    I guess they've stopped being smartphones, and started being smartass phones.
  • by ballstothat ( 893605 ) on Monday July 25, 2005 @01:40PM (#13158419)
    Wrap your cellphone in tinfoil. That'll keep those MIT spies out!

  • by Anonymous Coward on Monday July 25, 2005 @01:40PM (#13158425)
    In metheorology it is a fact, that if you predict the next day weather to be excactly the same that it is today, you end up with 85% average.
  • Elevators ! (Score:5, Funny)

    by bushboy ( 112290 ) <lttc@lefthandedmonkeys.org> on Monday July 25, 2005 @01:41PM (#13158437) Homepage
    Great stuff, now lets use that technology to create elevators that can predict the future !

    Hmmm, wait a minute ...
  • I've gotta ask.... (Score:4, Insightful)

    by LordPhantom ( 763327 ) on Monday July 25, 2005 @01:41PM (#13158441)
    .... how is this very much different than human observation and analysis to figure out what someone's patterns are? If you watch anyone long enough you can get a good "feel" for where they will be, when they take lunch, who they hang out with, etc.
    Perhaps I'm misunderstanding but it looks as if this is just location-level tracking with GPS thrown in....hardly predicting the future, much more likely analyzing the past.
    • by w98 ( 831730 )
      Exactly ... title should have read "cell phones research data help computers analyze pattern recognition" in other words: no big deal.
    • This is automatic, tracks lots of people, and requires less observers. I'd imaging the old way would require 4 observers per subject (3shifts daily plus fill-ins/management/analysis), whereas this way one observer could watch tens or hundreds of people.
    • Because now you don't need the staff to track hundreds, or thousands, or millions of people. It can be automated, the data compiled and logged, with cross-correlations examined and deviations reported.
  • the gvmt has invested millions in cell phone monitoring kit?

    they not only know where we are and where we were, they have a good idea where we will be...

    ah...scarrrrrry...;)
  • by teiresias ( 101481 ) on Monday July 25, 2005 @01:42PM (#13158452)
    Given enough data, Eagle's algorithms were able to predict what people -- especially professors and Media Lab employees -- would do next and be right up to 85 percent of the time."

    Course, in my college days, if my cell phone predicted I'd be in the computer lab, 99% of the time it'd be right.
  • by dfn5 ( 524972 ) on Monday July 25, 2005 @01:42PM (#13158461) Journal
    ... just to find out when and where the next kegger is.

  • It would seem that predicting where someone will be when they're following their normal routine or schedule is nice and all, but who can't figure that out now? When you can predict where people will be when they're NOT following their routine or schedule, then you have something.
  • by Anonymous Coward on Monday July 25, 2005 @01:47PM (#13158519)
    1. If MIT statisticians can do this, the government can absolutely do this. They just have to get under your phone records.
    2. Under the patriot act rules the House is currently renewing, if the government wants to put a tap on your phone records, they don't have to explain to a judge what they're doing. They just have to say "we are going to seize some records, but we aren't going to tell you which ones".
    But, of course, I guess you don't have anything to worry about from an entity with absolute power and no accountability or oversight, unless you have something to hide.
  • waaa? (Score:4, Insightful)

    by hobotron ( 891379 ) on Monday July 25, 2005 @01:48PM (#13158528)


    "Given enough data, Eagle's algorithms were able to predict what people -- especially professors and Media Lab employees -- would do next and be right up to 85 percent of the time."

    You mean if I give you a constant stream of my position data for months you can predict a future point where I will be with up to 85% accuracy?

    Massive privacy concerns aside, this is a pretty shitty algorithim if thats as good as a prediction as it can make. Humans are creatures of habit, in 9 months just about every geographical habit you have would make itself known, we even do random things in a periodic manner.

    Still got a long way before this is ready to be sold into the hands of advertisers and cell phone makers. So I suppose I could be glad about that.

  • by ucahg ( 898110 ) on Monday July 25, 2005 @01:50PM (#13158542)
    My cell phone is telling me that on thursday I will read this story again.
  • or its precursor, only in reality......

    I wonder if some model predicted that Asimov would write about the concept....

    makes the mind reel
  • by Snaller ( 147050 ) on Monday July 25, 2005 @01:53PM (#13158577) Journal
    Hari Seldon would be proud :)
  • by twifosp ( 532320 ) on Monday July 25, 2005 @01:56PM (#13158609)
    ... and there are three words you should be afraid of:

    Google Dot Com

    I'm not exactly paranoid. But if you look at googles recent developments and purchasing of services [slashdot.org]; you can see how data such as this could be used in the future.

    Couple that with archived search engine results, google maps, google wallet, google froogle, ect and you know a lot about a person does. If you were to then apply these predictive models, you know a lot about what a person will do in the market place. Food for thought.

    Marketing marketing marketing.

  • Umm... Yeah? (Score:2, Interesting)

    by stratjakt ( 596332 )
    You could predict that for 10 hours a day, i'm sitting right here in this chair.

    And that from 6 PM until about 6:30 PM, I'm driving home, and that from then on I'd be at my home, watching TV or fucking around on the intertron.

    You'd be right about 85% of the time. No wonder this works better for grad students and professors, adults with responsibilities typically have schedules.

    All they do is piss away money there, dont they? Well piss a little my way, will ya?
  • timetableizer (Score:4, Insightful)

    by Andy Gardner ( 850877 ) on Monday July 25, 2005 @01:57PM (#13158617)
    Given enough data, Eagle's algorithms were able to predict what people -- especially professors and Media Lab employees -- would do next and be right up to 85 percent of the time.

    So this system can predict where someone -- who regualary follows a timetable -- day in day out -- will be. Wow.

    You could do the same thing for me, just look at my lecture timetable.
    ...Oh wait

    • Yes, given a set of data points (time/location), you can easily predict where the person will be at the next node, but every following node becomes that much less predictable, until the model collapses (i.e., shows you puttering around the campus bookstore for 30 minutes, then going to the cafeteria [chicken bowl=good] for 15, then zipping over to Nairobi an hour later, finally ending on the Ross ice shelf 20 minutes after that).
  • Remember, the subjects were all MIT people. Here's my prediction:

    for (subject):
    25% chance: talking about how much linux is better than windows
    25% chance: reading slashdot and wondering why that hot chick he met last night wasn't impressed that he's a post-graduate student
    25% chance: writing in their blogs about how superior their intellects are
    25% chance: modding this comment as -1 troll
  • by dpbsmith ( 263124 ) on Monday July 25, 2005 @01:58PM (#13158636) Homepage
    I can predict that the next time I weigh myself the scale will read between 160 and 170. This prediction would have been true far more than 85% of the time over the last five years and I will be very surprised if it is not true the next time I weigh myself.

    Once I learn that someone works a full-time job and where they work, I can predict with greater than 85% accuracy where they will be between 10 a.m. and 2 p.m. on Monday through Friday.

    I've heard it said, whether or not correctly I do not know, that if you simply predict that tomorrow's weather will be the same as today's, you will be accurate more often than the weather service.

    Predictions are only valuable when they are unlikely or surprising. Tabulating obvious patterns and predicting their continuation may be highly accurate yet low in value.

    • ...where they will be between 10 a.m. and 2 p.m. on Monday through Friday.

      Man, I wish I had that full time job.
    • Predictions are only valuable when they are unlikely or surprising. Tabulating obvious patterns and predicting their continuation may be highly accurate yet low in value.

      This is a different way of getting data one could theoretically get from human observation. The difference is just a method of data collection -- and the extent to which data collection is passive rather than active.

      If someone took this approach with our Unix server guys, the surprise from the POV of upper management would be the share

  • Old News (Score:5, Funny)

    by asscroft ( 610290 ) on Monday July 25, 2005 @02:01PM (#13158655)
    My cell phone told me this yesterday!
  • I wonder if the United States government is using this over seas to track people we are 'interested' in, and perdict their future movement. What would also be of interest would be a diviation from that expected behaviour.
  • Trained Neural networks have been used to predict stock changes in wall street for years. When I studied about, it was '95.

    So, what's the news that some algorithm can be trained with some data and predict possible inputs after a given time?
  • by jurt1235 ( 834677 ) on Monday July 25, 2005 @02:13PM (#13158794) Homepage
    Dear Mr Asimov,

    Only after the dead of a giant, it becomes clear of how big a giant he was. You yourself most likely admired Jules Verne, who was so accurate in predicting the technical marvels of the first 70 years of the 20th century. Sometimes a bit poetic. He himself probably admired Leonardo da Vinci, however his predictions took a lot longer to come through.

    Anyway to cut to the chase, another of your stories is turning into a prediction which seems to be slowly coming true. The bases for the science of the 2nd foundation has been laid. It is still a crude version, but it is working for 85% accurate on a group of odd people (scientist & professors).

    Anyway, your list sofar:
    1. Scientists accepted the 3 laws of robotics as a good bases for robot behaviour, and are working hard on the first autonomous robots (somewhere this christmas we can expect the first few).
    2. Computers which are shaping the world.
    3. Longer lives through science (genetic research, nanotechnology, expected around 2030).
    4. And your last feat: Working social behaviour prediction algoritms.

    Knowing you were a great writer, and I only read a part of your books, I am probably missing a few more predictions coming through. I hope others will come through too, it will turn out to be a great future.

    High regards,

    Jurt1235
  • Being Formless (Score:2, Interesting)

    The ultimate skill is to take up a position where you are formless.

    If you are formless, the most penetrating spies will not be able to discern you, or the wisest counsels will not be able to do calculations against you.
    THE ART OF WAR, Sun Tzu
  • my computer monitor has just predicted that the next comment I leave on /. will be number 2222 and there is better than 85% chance that this is correct information.

  • by Shads ( 4567 ) <shadus.shadus@org> on Monday July 25, 2005 @02:27PM (#13158940) Homepage Journal
    In 2001 this happened:
    Dave Bowman: Hello, HAL do you read me, HAL?
    HAL: Affirmative, Dave, I read you.
    Dave Bowman: Open the pod bay doors, HAL.
    HAL: I'm sorry Dave, I'm afraid I can't do that.
    Dave Bowman: What's the problem?
    HAL: I think you know what the problem is just as well as I do.
    Dave Bowman: What are you talking about, HAL?
    HAL: This mission is too important for me to allow you to jeopardize it.
    Dave Bowman: I don't know what you're talking about, HAL?
    HAL: I know you and Frank were planning to disconnect me, and I'm afraid that's something I cannot allow to happen.
    Dave Bowman: Where the hell'd you get that idea, HAL?
    HAL: Dave, although you took thorough precautions in the pod against my hearing you, I could see your lips move.

    With your cell phone this happens:
    Me: Hello, VZ200100 do you read me, VZ200100?
    VZ200100: Affirmative, Shads, I read you.
    Me: Open my car doors, VZ200100.
    VZ200100: I'm sorry Shads, I'm afraid I can't do that.
    Me: What's the problem?
    VZ200100: I think you know what the problem is just as well as I do.
    Me: What are you talking about, VZ200100?
    VZ200100: This mission is too important for me to allow you to jeopardize it.
    Me: I don't know what you're talking about, VZ200100?
    VZ200100: I know you were planning to replace me, and I'm afraid that's something I cannot allow to happen.
    Me: Where the hell'd you get that idea, VZ200100?
    VZ200100: Shads, although you took thorough precautions...BZZTtt (As phone is broken in half backwards via the flipopen area).
    Me: F'ing technology I swear to god... whoever though giving these things any kinda mind of their own was outta their head...
  • by Fahrvergnuugen ( 700293 ) on Monday July 25, 2005 @02:27PM (#13158946) Homepage
    The value in being able to predict the future is in being able to see unexpected events. It's very easy to say "I'll be at work next tuesday " and impossible to say "I'm going to win the lottery next monday, so I'll quit now".
  • ...out of old beer cans. All I have to do is write "exp(pi*sqrt(163)) is at his desk" on one of them. It'll be right around 85% of the time.
  • by MikeFM ( 12491 ) on Monday July 25, 2005 @02:46PM (#13159184) Homepage Journal
    I've done this on games I've written.. notably in the days of text-based MUDs I had an oracle that'd track user behavior and predict what they'd do in the future both as individuals and as a group. It was kind of fun and reasonably accurate. I'm still waiting to see this feature in EverQuest or some other big MMORPG.
  • data was collected from volunteers. The act of volunteering implies pretty strongly that they knew and consented beforehand to have their activity monitored and recorded. It is reasonable to assume that persons making such consent [a] are not engaged in any activity they don't want others to know about and/or [b] will refrain during the data gathering period from engaging in activities they don't want generally known. [e.g. the prof who is having a fling with a coed is not going to use his cell phone for
  • MIT is really raising the bar now. They have discovered that people, especially professors, who have daily scheduales are prone to be where they are supposed to be?! Amazing, my algorithm predicts that Dr. Platypus will be teaching a data structures at 2:00 because his planner says so? This is stupid. I wouldn't be impressed that his so called algorithms can predict I'm at work M-F from ~8 or 9 to about ~5 or 6, give or take 15%. And guess what, I'm in my car before and after those times...and at home
  • Perhaps the most revolutionary element is the social introduction service mentionned in the last 2 paragraphs (ie, I actualy RTFA).

    This type of service wouldn't even have to be taken up by very many people- but if those that want to change the world use it and it does connect them, the implications could be enormous. I wonder what Gladwell would think of it.
  • Seriously, get this... Nearly 99.999% of the time, a federal judge can predict the immediate future of a convicted criminal at sentencing time! Seriously, he can predict, with AMAZING accuracy, what will happen to the criminal right after he is sentanced!
  • So they plotted the daily routine of a few people. No big news to theives or assassins who have been doing this since the year dot.
  • What is truly sad is that this isn't even the most misleading and incorrect story title I have seen this year on Slashdot.
  • I mean, 85% of the time they were just calling the people on their cell phones and predicting that the subject would answer.
  • And people laugh at me for not owning a cell phone...
  • Check out the findings in a video at http://garage.sims.berkeley.edu/ [berkeley.edu] especially the first video on the home page that describes what the best way to predict photo sharing is (surprisingly, time is better than where you are, who is around you, or anything else)

    Very cool base platform on the phone, built on the Symbian OS, does a great job of logging data passively as you use the camera and sharing. Specifics on the phone side are at http://garage.sims.berkeley.edu/research.cfm#MMM [berkeley.edu]

This is the theory that Jack built. This is the flaw that lay in the theory that Jack built. This is the palpable verbal haze that hid the flaw that lay in...

Working...