Adobe Social gets predictive tool for hyper-targeting
Nancy Owano, Apr 27, 2013
Predictive analytics technology offers predictive data for customers, to optimize the marketer's efforts to increase customer responses and clicks. The data analyses can be used to guide future actions that can produce best results.
...new capability offers predictive analytics, historical data-driven recommendations, self-learning (the solution learns as it goes, with continual refinements to its recommendations) and social content optimization (best time to post).
"Traditionally, social posts are composed without a measurable, data-driven connection to how they will be received, and many marketers release big news or compelling content through social channels only to find that it falls flat in terms of engagement," according to an Adobe statement about its beta.
How it works: Customers open a widget showing an estimated range for the amount of Likes, comments, and shares a post will receive. They can identify other metrics, too, for tracking. Another key Adobe Social feature is timing. The tool will indicate if the post had best be delayed for posting later. Posts are not just targeted but (using Adobe's lingo) "hyper-targeted."
More information: www.adobe.com/solutions/social-marketing.html
Scientists identify a mathematical 'crystal ball' that may predict calamities
Oct 28, 2013, phys.org
Neuroscientists have come up with a mathematical equation that may help predict calamities such as financial crashes in economic systems and epileptic seizures in the brain.
...measure of 'information flow' reaches a peak just before a system moves from a healthy state to an unhealthy state. Such 'phase transitions' are common in many real systems, and are often highly significant: epileptic seizures and financial market crashes are just two examples of transitions.
Lead researcher Dr Lionel Barnett says: "The key insight in the paper is that the dynamics of complex systems – like the brain and the economy – depend on how their elements causally influence each other; in other words, how information flows between them. And that this information flow needs to be measured for the system as a whole, and not just locally between its various parts."
Essentially this means finding a way to characterize, mathematically, the extent to which the parts of a complex system are simultaneously segregated (they all behave differently) and integrated (they all depend on each other).
Surprising results from study of non-epileptic seizures
Loyola University Health System, link
Study finds evidence that stock prices can be predicted within a short window of time
Feb 04, 2014
The study by researchers in the Tippie College of Business suggests that price movements can be predicted with a better than 50-50 accuracy for anywhere up to one minute after the stock leaves the confines of its bid-ask spread. Probabilities continue to be significant until about five minutes after it leaves the spread. By 30 minutes, the predictability window has closed.
IBM researchers' algorithm explores tweets for home location cues
Mar 24, 2014
From July 2011 to Aug 2011, they collected tweets from the top 100 cities in US by population. They invoked the Twitter REST API to collect each user's 200 most recent tweets (less if that user had fewer than 200 total tweets). Some users discovered to have private profiles were eliminated. The final data set had 1.5 million tweets by 9551 users.
In listing their contributions, the IBM researchers said, when tested using the 1.52-million tweet dataset from 9551 users from 100 US cities, that their algorithm outperforms the best existing algorithms for home location prediction from tweets. "Our best method achieves accuracies of 64% for cities, 66% for states, 78% for time zones and 71% for regions."
More information: Home Location Identification of Twitter Users, arXiv:1403.2345 [cs.SI]
[just to point at that is must be easier to predict timezone and region based on time-patterns (people sleep at the same time, for the most part, and this shifts based on time-zones; each region brings a particular vocabulary and vernacular, place names alone, in large enough quantities, can give a good sense of where a person is, regionally.]
Forecasting future may one day become as practical as predicting weather, thanks to Big Data advances
Jun 27 2014, phys.org
Early Model Based Event Recognition using Surrogates project, or EMBERS—Virginia Tech
In the past year, the team has used such an approach to correctly forecast many important events such as the riots after Paraguay's president was impeached, the Hantavirus outbreaks in Argentina, and the recent mass protests in Brazil and Venezuela.
One thing this particular program does is read images of parking lots outside of health centers and hospitals to monitor upticks in "fill rate."
Anil Vullikanti, a panelist and an associate professor of computer science, had many anecdotes regarding the role of human intervention in data forecasting.
"You will always have people intentionally trying to clog the system with misinformation to throw you off course, but we are trained to separate the signal from the noise and minimize distractions."
Interestingly enough, the spread of an idea is not so different from the spread of an illness.
"Let's say you can predict the future and you intervene to prevent an uprising," Parikh says. "How can you be sure that an uprising was actually going to happen?"
Just four bits of credit card data can identify most anyone
phys.org, Jan 2015