Data Intelligence, Business Analytics
Added by Vincent Granville on February 1, 2012 at 10:51am — No Comments
ADaBoost.M1 tries to improve step by step the accuracy of the classifier analyzing its behavior on training set. (Of course you cannot try to improve the classifier working with the test set!!).
Here lays the problem, because if we choose as "weak algorithm" an SVM, we know that almost always it returns excellent accuracy on the training set with results closed to 100% (in term of true positive).
In this scenario, try to improve the accuracy of classifier assigning different weights…
Added by Cristian Mesiano on January 30, 2012 at 2:06pm — No Comments
The complaint is also about the fact that Microsoft, located in Redmond, Washington, can't find local candidates and has to hire candidates from out-of-state (and I guess, from out-of-country), to fill big data, IT, data scientist and engineering positions. There was a long article today in the Seattle Times about how terrible Washington State is - according to Brad Smith - in terms of educating its citizens.…Continue
Companies are getting smarter at predicting your next move.…Continue
Added by Vincent Granville on January 29, 2012 at 7:00pm — No Comments
Big data is hot, but infrastructure-level platforms such as Hadoop, which focus on storage and processing, still need help to…Continue
Added by Vincent Granville on January 29, 2012 at 3:51pm — No Comments
The June 2008 issue of Computational Statistics and Data Analysis covered an analysis of Excel 2007. These faults and errors are being reviewed for inclusion.
Section 20 has been rewritten with new material based on errors pointed out by Paulo Tanimoto.…
Copula Dependence Structure on Stock Market with Application to Risk
Department of Mathematical Statistics
CHALMERS UNIVERSITY OF…
Added by John A Morrison on January 28, 2012 at 12:00am — No Comments
MINNEAPOLIS, Jan. 26, 2012 /PRNewswire/ -- FICO (NYSE:FICO - News), the leading provider of analytics and decision management technology, announced today that William J. Lansing, a 30-year veteran in the technology industry and a current member of the FICO board of directors, has been appointed chief executive officer of FICO, effective January 27, 2012.
Mr. Lansing succeeds Dr.…Continue
Added by Amy on January 27, 2012 at 3:30pm — No Comments
At North Carolina State, an advanced analytics program lasting 10 months has, since its founding in 2006, placed over 90 percent of its students annually. The average graduate’s starting salary for an entry-level job is $73,000. Its current class of 40 students had 185 applicants, and next year’s applications are already twice that. In 2009, Harvard awarded four undergraduate degrees in statistics. Two graduates…Continue
Added by Amy on January 27, 2012 at 10:00am — No Comments
The science of…
Added by Gerhard Furter on January 25, 2012 at 1:48pm — No Comments
Another recent article from Discovery Corps, Inc. president Tim Graettinger: Grab Bag 2: More Frequently-Asked Questions about Data Mining.
"While helping present a monthly webinar on Data Mining, I'm asked some challenging and really pivotal questions about DM and predictive analytics:
Have a cool idea for a product related to data or personalization? We’ll help you build it! The Rapleaf Personalization Fund is $1 million of cash and in-kind awards (plus invaluable support from our partners) for cool startups that integrate with our data. We’re looking for awesome start-ups based on Rapleaf data that will take personalization to the next level.
Added by Vincent Granville on January 22, 2012 at 3:30pm — No Comments
When you do a book search on Amazon using keywords, in the search result page you see 16 results. If you've bought one (or more) of these books, it still shows up on the search result page. It would be easy to eliminate that book that you already purchased (e.g. by showing it at the bottom of the page), and replacing it by another book that you haven't purchased yet. Sounds to me like an obvious, simple optimization trick. Maybe Amazon's statisticians use very complex models that change…Continue
Added by Marcel Remon on January 21, 2012 at 10:06pm — No Comments
Traditional religions have existed for more than a thousand years, and are usually based on a system of illogical, incompatible dogmas, which can't be modified without killing the whole concept. This is especially true for more conservative flavors such as integrism.
One of the concepts that has resisted time, in many religions, is God: it is traditionally presented as good guy (except that He is bad with those believing in the wrong religion), personified as an old,…Continue
Interesting blog post by SmartAnalytics
Added by Vincent Granville on January 21, 2012 at 7:12pm — No Comments
The crisis in the socio-economic continuum of modern civilization - as a historic challenge to a qualitatively new role of socio-technologies for the expansion of consumption and market diversification is not so much a real possibility - but there is a historical inevitability ... .
Modern civilization has undoubtedly in many respects, the main product of the market economy and market relations. And the social foundations of the…
Added by Oleg Mazukabzov on January 21, 2012 at 10:03am — No Comments
Tulsa, OK – January 19, 2012 - StatSoft announced that its STATISTICA release has achieved certified integration with the SAP NetWeaver® technology platform. STATISTICA, StatSoft’s flagship analytics software platform, works with…Continue
Added by Vincent Granville on January 20, 2012 at 9:00am — No Comments
It's interesting when I read dismissive blogs about 'Point in Time' data suggesting it's no longer relevant. I would like to introduce one fundamental data type that does not change and directly impacts business performance: talent analytics. These are numbers representing stable characteristics about how we work naturally and what we are driven by. Think of them as your strengths in numbers form.
Since we all have people in our lives, I don't need to post 10 links…Continue
Added by Mike Kennedy on January 19, 2012 at 10:30am — No Comments
Point in Time (PiT) v Through the Cycle (TTC)
There used to be an argument about this; its clear to me now that this is more than an arithmetic conundrum about Ratings and RWAs its a philosophical matter applicable to wider aspects of life & thus any arguments for PiT are just lazy and myopic. Here are some good recent references; I have selected recent papers since the debate has evolved towards a conclusion since it first developed 2 or so years ago. The game has…Continue
Added by John A Morrison on January 19, 2012 at 5:17am — No Comments
For places such as the Pacific Northwest, UK or Germany, where weather is highly volatile, I believe that my mentor's model (when I did my PhD) might actually be the best one. In places where weather is easy to predict by looking at satellite images, you might be able to do well without any model.
The model described below is based on data from the Puget Sound (Seattle) area. For many years, weather forecasts for the Seattle area have been notoriously erroneous.…Continue