KDnuggets™ News 10:n19, Aug 11

Features (5) | Software (4) | Jobs (12) | Meetings (2) | Publications (4) | NewsBriefs (5) | CFP (6) | Quote

Features

• New Poll: Switching from SAS to WPS ? - Aug 10, 2010.
  Are you considering a switch from SAS in light of recent WPS victory in court?
• P != NP finally proved ? - Aug 9, 2010.
  P != NP is probably the most important problem in theoretical computer science, with $1M prize. Vinay Deolalikar at HP Labs has released a preliminary 100+ page proof that P != NP.
• Poll results: Many Data miners prefer to analyze social networks than participate - Aug 10, 2010.
  42% of respondents prefer to analyze social networks, but not participate
• Most viewed items for week Aug 1-7 - Aug 8, 2010.
  The Most Comprehensive Social Media Analytics Platform List; Poll Results: Data types analyzed;
  Top jobs: Research Scientist, Data Mining & ML at Siemens Corporate Research, NJ; Risk Forecasting Analyst at CashEdge, CA or NY;
• KDnuggets 1000 Twitter followers word cloud - Aug 7, 2010.
  Prominent keywords include Data, analytics, media, social, phd, business, student, online, mining.

Software (see also All Software)

• Revolution Analytics Brings Big Data Analysis to R - Aug 7, 2010.
  R language can now tackle terabyte-class data sets using Revolution R Enterprise-at a fraction of the cost of legacy analytics products
• Another NZ bird - MOA: Massive On-line Analysis environment - Aug 5, 2010.
  MOA is a framework for data stream mining, with tools for evaluation and a collection of machine learning algorithms. Related to the WEKA project, also written in Java, while scaling to more demanding problems.
• Meet the Big Data Equivalent of the LAMP Stack - Aug 5, 2010.
  What's been missing for Big Data analytics has been a LAMP (Linux, Apache HTTP Server, MySQL and PHP) equivalent. Fortunately, there's an emerging LAMP-like stack for Big Data aggregation, processing and analytics
• New competition: Chess ratings - can Kagglers do better than Elo? - Aug 5, 2010.
  Can you come up with a better rating system for predicting outcome of chess games between experts?

Jobs (see also All Jobs)

• Pre-Sales Engineer in Predictive Analytics at Predixion Software, Orange County, CA or Redmond, WA - Aug 10, 2010.
  pre-sales expert to join our team of industry veterans and development rockstars to help close large enterprise accounts.
• Director of Research, Algorithms and Data Mining at JustAnswer, San Francisco, CA - Aug 10, 2010.
  What if your work in algorithm development could help save lives? At JustAnswer, it could! We're the largest paid question and answer platform, where thousands of Doctors, Lawyers, Veterinarians, Mechanics, and other Experts answer questions 24/7
• Software/Algorithms Engineer at Efficient Frontier, Sunnyvale, CA - Aug 9, 2010.
  Architect and implement ad targeting models that use advanced statistical and machine learning techniques; develop and implement algorithms that work with large scale data for forecasting and optimizing return on display advertising spend.
• Junior Analytics Manager at Opera Solutions, San Diego, Jersey City, New York, USA - Aug 8, 2010.
  responsible for the quality of analytical projects or a single class of models within a market effort.
• Analytics Manager at Opera Solutions, San Diego, Jersey City, New York, USA - Aug 8, 2010.
  design, develop, and deploy state-of-the-art, data-driven predictive models to solve business problems using the latest and most appropriate technologies in machine learning, statistical modeling and operations research.
• Statistician - Client Analytics at UBS, Weehawken, NJ - Aug 6, 2010.
  work with our internal business partners in defining, executing and delivering data analytics that support their decision making and targeting efforts.
• Senior Predictive Modeler at Allstate Research and Planning Center (ARPC), Menlo Park, CA - Aug 6, 2010.
  seeking a highly experienced predictive modeler for the role of Principal Scientist in its Analytics Group.
• Senior Software Development Engineer at Bing, Microsoft, Bellevue, WA - Aug 5, 2010.
  Analyze & process a huge amount of data by using data mining, statistics, and database techniques. The goal is to measure/understand user experience, system performance, and business health, generate actionable insights for improving search systems, and increasing user satisfaction.
• Principal Lead Researcher at Bing, Microsoft, Bellevue, WA - Aug 5, 2010.
  The Bing Data Mining Team is hiring extremely talented, highly motivated and productive lead with expertise in the areas of analytics, statistics, machine learning, and data mining.
• Reporting & Analytics Manager at Walt Disney's Parks and Resorts, Orlando, FL - Aug 4, 2010.
  Execute campaign performance and analysis by using SAS. Develop insights to optimize campaign performance by employing data mining tools/techniques to discover relationships and patterns utilizing various sources of data.
• CMR Technology Development Manager at Walt Disney's Parks and Resorts, Orlando, FL - Aug 4, 2010.
  Manage all aspects of Disney Parks Merchandise technology integration as it relates to CMR initiatives, including data integration, marketing tactics, lead generation, conversion and retention, and descriptive analytics. Use SAS and SQL technologies for data discovery and analysis.
• CMR Platform Development Manager at Walt Disney's Parks and Resorts, Orlando, FL - Aug 4, 2010.
  The Customer Managed Relationship (CMR) organization is responsible for developing an overall customer centric relationship strategy at a one to one level with a goal to help Guests create the most magical vacation experience possible.

Meetings (see also All Meetings)

• Data-driven journalism: What is there to learn? - Aug 6, 2010.
  On Aug 24, in Amsterdam, this conference will bring together journalists and specialists in data mining, data visualisation and multimedia.
• PAKDD 2010 Awards - Aug 5, 2010.
  Awards presented at the PAKDD 2010, 14th Pacific-Asia Conference on Knowledge Discovery and Data Mining, held in Hyderabad, India in June 2010.

Publications

• What is in common between Aristotle, A-bomb and data mining? - Aug 10, 2010.
  An amazing story of John Aristotle Phillips, the founder of Aristotle political data mining company
• Validating the Logistic Regression Model - Aug 9, 2010.
  The purpose of this write-up is to introduce the principal features of a bootstrap validation method for the ever-popular logistic regression model.
• SAS, WPS and R - Aug 8, 2010.
  In a decision that that could have major impact on the analytics marketplace, the UK High Court has ruled against statistical giant SAS in its litigation of tiny UK upstart World Programming Ltd (WPL).
• Sites Feed Personal Details To New Tracking Industry - Aug 6, 2010.
  WSJ: The 50 largest US sites installed on average 64 tracking files on the visitors' computers. The tracking files represent the leading edge of a lightly regulated, emerging industry of data-gatherers who are in effect establishing a new business model for the Internet.

News Briefs

• Last 4 weeks of IEEE ICDM Contest. Still time to join and win $5K of prizes - Aug 9, 2010.
  Half of the ICDM 2010 Contest organized by TunedIT for IEEE International Conference on Data Mining had already passed. 460 teams have registered so far and over 60 of them submitted one or more solutions.
• San Antonio Spurs select SAS(r) Analytics - Aug 10, 2010.
  Spurs found an analytics advantage with SAS Visual Data Discovery
• LinkedIn Acquires mSpoke For Its Recommendation Technology, Team - Aug 9, 2010.
  mSpoke is a small Pittsburgh startup with recommendation technology that helps to make content more relevant.
• ID Insight patent to help prevent identity theft - Aug 7, 2010.
  for innovative method of identifying address differences to help banks and other financial institutions detect and prevent identify theft.
• B-Schools All A-Twitter Over Social Media - Aug 5, 2010.
  With interest in social media growing, B-schools are adding courses to teach students what it means for business

CFP - Calls for Papers (see also All CFP)

• PAW 2011 - San Francisco, due Oct 8
• PAKDD-2011 Workshop Proposals, due Aug 29
• PAKDD 2011, due Sep 19
• KD-2010, due Sep 20
• PAW 2011 - San Francisco, due Oct 8
• SIAM Data Mining 11, due Oct 15

Quote

The important thing in science is not so much to obtain new facts as to discover new ways of thinking about them.

William Lawrence Bragg