Posts Tagged ‘predictions’
Supercomputer Reads the News to Successfully Forecast World Events
Kalev Leetaru of the University of Illinois determined that using the Nautilus SGI supercomputer to analyze news stories can help predict major world events. The analysis he used for the experiment was retrospective, feeding the computer millions of articles from which it was able to determine a deteriorating national sentiment towards Libya and Egypt before the revolutions in those countries. The system was also able to narrow down Osama Bin Laden's location to within 125 miles before he was found and killed last May.
More than 100 million articles were gathered for this study, from various sources including the New York Times archive, Open Source Center and BBC Monitoring (two organizations that monitor local media output worldwide). The system searched for two primary things in the articles: mood and location. Words such as “nice” or “horrible” were used to measure mood, and geocoding converted mentions of places such as “Cairo” or “Pakistan” to plottable coordinates.
For countries that experienced the “Arab Spring,” the supercomputer produced graphs that showed a noticeable decline in media sentiment both within each country and without. Before President Mubarak's resignation, the tone of media coverage of Egypt fell to one of its lowest points in 30 years, predicting something that U.S. government could not. As Leetaru told BBC news, the president's continued support of Mubarak showed that high-level analysis suggested Mubarak wasn't going anywhere. The graph, however, suggests otherwise.
Leetaru's next step is developing technology to allow this system to forecast major world events, rather than just analyzing them after the fact. He compares it to economic forecasting algorithms, as well as meteorology, in that none of those systems (including his) are perfect, but using them is far better than just guessing.
[BBC]
Supercomputer Reads the News to Successfully Forecast World Events
Kalev Leetaru of the University of Illinois determined that using the Nautilus SGI supercomputer to analyze news stories can help predict major world events. The analysis he used for the experiment was retrospective, feeding the computer millions of articles from which it was able to determine a deteriorating national sentiment towards Libya and Egypt before the revolutions in those countries. The system was also able to narrow down Osama Bin Laden's location to within 125 miles before he was found and killed last May.
More than 100 million articles were gathered for this study, from various sources including the New York Times archive, Open Source Center and BBC Monitoring (two organizations that monitor local media output worldwide). The system searched for two primary things in the articles: mood and location. Words such as “nice” or “horrible” were used to measure mood, and geocoding converted mentions of places such as “Cairo” or “Pakistan” to plottable coordinates.
For countries that experienced the “Arab Spring,” the supercomputer produced graphs that showed a noticeable decline in media sentiment both within each country and without. Before President Mubarak's resignation, the tone of media coverage of Egypt fell to one of its lowest points in 30 years, predicting something that U.S. government could not. As Leetaru told BBC news, the president's continued support of Mubarak showed that high-level analysis suggested Mubarak wasn't going anywhere. The graph, however, suggests otherwise.
Leetaru's next step is developing technology to allow this system to forecast major world events, rather than just analyzing them after the fact. He compares it to economic forecasting algorithms, as well as meteorology, in that none of those systems (including his) are perfect, but using them is far better than just guessing.
[BBC]
Surprise, surprise: Apple’s iPad expected to dominate tablets into 2012
Even though we’re seeing a slew of Android tablets on the horizon, Apple’s iPad is expected to maintain its leading place in the tablet market into 2012, according to J.P. Morgan analyst Mark Moskowitz.
This, of course, should surprise no one. The iPad sparked the most recent tablet craze when it was announced early last year, this after the tablet market saw several false starts over the past few decades.
Moskowitz predicts tablet revenues will rise to $24.9 billion in 2011 (up from $10.2 billion this year) and that they’ll hit $34.1 billion in 2012. The iPad, which will make up for 89.4 percent of tablet revenues this year, will still account for a significant portion of total tablet revenues in the next few years. In 2011, he predicts the iPad will account for 71.6 percent of tablet revenue, and by 2012 it will still lead with 61.4 percent.
Apple in the iPad’s first six months, and some analysts predict . The iPad has a significant head start on its rivals, and it also boasts more polished software — Android isn’t expected to be optimized for tablets until its version 3.0 release in the first half of 2011. Moskowitz also expects Android 3.0 to be released some time around the release of the second generation iPad, which should dull the impact of Android tablets even further.
Via
Companies: ,
People:
Study Shows Some Evidence Of Human Precognitive Powers
In particular, "participants correctly identified the future position of erotic pictures"
That’s not to say that storefront psychics really can read your palm, or that one can see the future simply by thinking hard about it. But Bem’s empirical, straightforward science suggests the brain does have some ability to perceive what’s coming. The science is sound enough that Bem’s paper found a home in the prestigious Journal of Personality and Social Psychology, which will publish the piece shortly. It also received a fairly lengthy write-up in .
Bem’s research on what he calls psi – meaning “anomalous processes of information or energy transfer that are currently unexplained in terms of known physical or biological mechanisms” – attempts to explore and explain precognition (conscious awareness of a future event) and premonition (affective apprehension of a future event). To do so he conducted nine experiments on more than 1,000 Cornell students.
For an in-depth break down of Bem’s methodologies, you can access a preview of (PDF). But his methodology is consistent throughout: Take an established psychological response to a certain stimuli, then flip it around so the stimulus comes after the response and see if the response is still the same. The results weren’t overwhelming, but they were statistically significant.
For instance, in one experiment Bem gathered 100 subjects, half male and half female. Using a computerized system, they then played a game in which two curtains were displayed on the screen and the subjects had to choose which one had a picture hiding behind it. Some of these pictures were neutral in content. Others were chosen at random by the computer from a database of semi-erotic and erotic photos (hey, looks like science isn’t boring after all).
The result: In cases where an erotic photo was lurking behind the curtain the subjects were able to accurately identify which curtain it was behind with 53.4 percent accuracy – not a huge statistical spike but significantly better than the 50 percent accuracy rate that could be expected by chance. The accuracy rates were not as high for non-stimulating images, which fell more or less in line with raw statistical chance. This suggests that the subjects could somehow sense the erotic stimuli that awaited them before it happened.
In another experiment Bem reversed the priming effect wherein subjects are subliminally tipped off before identifying a photo as positive or negative. Bem found that by subliminally tipping off subjects after – rather than before – showing the image, they still were able to categorize the pictures more quickly as if the brain knew that the subliminal hint was coming even though it hadn’t happened yet.
We won't declare the Earth shattered just yet, but other cognitive researchers are taking notice of Bem's work. Apparently there have been hundreds of requests for so other scientists can re-test Bem’s experiments and see if the results come back the same. If they do, we may have to reconsider how we perceive our own cognition. But you already knew I was going to say that, didn’t you?
[]
Future-Predicting Search Engine Reveals Some of the Analytical Tricks Inside Its Crystal Ball
Speaking to Technology Review, company founder Christopher Ahlberg described how its software goes deeper than search engines like Google that simply rank the relevance of results by links. Rather, it analyzes the more nuanced, invisible connections between events and people that shape the future. Doing so, he says, lets Recorded Future look for patterns that suggest certain outcomes, like when a product might release or when a company might clear a patent hurdle or offer an IPO.
Recorded Future’s software does this semantically, using linguistic tools that identify certain types of events and the sentiment conveyed in the wording. It aims for articles with some degree of established veracity, like government filings, news articles, and speeches by leaders or heads of industry, but the software also scans Twitter updates and other measures of general feeling or sentiment surrounding an event, person, company, or product.
In other words, it’s less a matter of Recorded Future wagering an educated guess about a future event and more like an aggregation of predictions that have already been made. That aggregate collated prediction about the future is influenced by all the factors listed above and gives, say, a stock analyst a reasonable measure of when an event is likely to happen.
Right now Recorded Future has fewer than 100 clients paying to use its tools, but those that are using them aren’t lightweights – Ahlberg tells TR a mix of government analysts and financial firms are taking advantage of the insight the company offers. Those are players whose decisions are tied to serious stakes in both security and finance, lending Recorded Future an air of serious credibility. Indeed, studies of its past performance have shown its models tended show increased strength of activity around an event or entity that correlated to real time market activity.
Which means Recorded Future, and analytic tools like it, might have a future after all.
[]
Europe’s Living Earth Simulator Could Forecast the Future
The goal would require gathering unprecedented amounts of information about the planet and its societies
Such "reality mining" would track everything from financial transactions to individual travel itineraries, from medical records to carbon dioxide emissions. If computer modelers can pull off the feat of simulating not only the planet's systems but also every one of its inhabitants, it could potentially lead to simulating the future in a way similar to how weather forecasters predict the weather.
That astounding vision is the brainchild of Dirk Helbing at the Swiss Federal Institute of Technology in Zurich. Helding's desire for such real-time knowledge of the Earth stems from his leadership in the emerging field of techno-socio-economic studies, and perhaps reading a bit much of Isaac Asimov's Foundation series and dreaming of psychohistory's predictive powers.
Plenty of supercomputers already run complex simulations focused on financial markets . NASA has also joined forces with Cisco to launch a $100 million network that integrates all sorts of ground, sea, air and space sensors -- perhaps a bit of a precursor to what Helding has in mind.
That's not to say that the project might not need a heck of a lot more money than $1.3 billion, assuming that the European Commission approves it. But Technology Review suggests that the alternate to a publicly funded effort is a darker vision of such predictive power in the hands of a single corporation, or perhaps one nation's military. In that spirit, we'd suggest that there's no time like now to start -- hopefully any such model incorporates the zoom and swoop options available in Google's engine.
[via ]
Twitter Buzz Predicts Box-Office Success Better Than Hollywood Stock Exchange
Social media predictive power might also extend beyond box office success
Sitaram Asur and Bernardo Huberman of HP Labs kept track of movie mentions on among 2.9 million tweets from 1.2 million users for three months. Their sample focus included 24 movies such as and Twilight: New Moon.
For opening weekend, their computer model monitored the rate of tweets near a movie's release date and also factored in the number of theaters showing the flick. That allowed the model to predict the opening weekend revenues with 97.3 percent accuracy, compared to the Hollywood Stock Exchange's 96.5 percent accuracy.
For the second weekend, the model examined both tweet rates and the ratio of positive to negative tweets. That different approach reflects second-weekend performance success based on word-of-mouth, rather than opening-weekend performance buzz. Again, the model delivered quite splendidly with 94 percent accuracy.
There's a few caveats to keep in mind, such as the fact that the Twitterati represents a certain self-selecting slice of society. One expert told Fast Company that he suspected Twitter might do better for predicting "upmarket" films aimed at somewhat older audiences, given the social media service's user base.
But there's an exciting possibility for extending Twitter's predictive power beyond movies, the researchers say. A similar model could apply for any number of commercial products beyond Hollywood fare, and might work especially well for products or trends that lack prediction markets such as the Hollywood Stock exchange. Presidential , anyone?
Twitter might even go beyond a mere forecasting service for commercial success. suggested that the social media service could also allow marketers to directly influence the success of their product by boosting tweet rates -- although we assume that strategy would require more savvy than using obvious Twitter bots.
There's also a good opportunity here for savvy prediction market players, if they can apply a bit of Twitter analysis to how they play the Hollywood Stock Exchange. We hear that HSX has recently transitioned to real money.
[via ]