KDnuggets™ News 11:n22, Sep 14

Features (9) | Courses, Events (6) | Webcasts (1) | Software (4) | Jobs (6) | Academic (3) | Competitions (2) | Meetings (2) | Publications (7) | NewsBriefs (6) | CFP (6) | Quote

Features

• New Poll: Is Data Science different from Statistics? - Sep 13, 2011.
  Please vote in KDnuggets poll: How different is "Data Science" from "Statistics" ?
• Poll Results: What do you call analyzing data? - Sep 13, 2011.
  Data mining is still the most top term, but the 2nd most popular terms differ for Industry and Academia. The least common term is surprising. We also analyze the "bias" of each term with respect to usage in Industry.
• Connecting with the Social Analytics Experts - Sep 7, 2011.
  Text Analytics News caught up with four analytics leaders who are helping connect and educate analytics professionals on the Web.
• Interview with Eric Siegel - Why should you come to PAW NYC? - Sep 12, 2011.
  Predictive Analytics World is the leading and largest cross-vendor conference covering commercial deployment. There's nowhere else you'll find as much content and as many leading experts.
• How to find data miners, analytics people, and data scientists - Sep 3, 2011.
  Do you want more friends that understand cross-validation error, overfitting and SVM?
• Top news for Sep 4-10 - Sep 11, 2011.
  SAS vs R discussion; Top KDD references from the last 4 years;
  Top jobs: Predictive Modeler at Allstate Research/Planning Center; PhD Position in Medical Data Mining at Maastricht U.
• Top news for Aug 28 - Sep 3 - Sep 4, 2011.
  New Poll: What do you call data mining? Fake reviews online; Big data revolution: 5 startups mining the trend;
  Top jobs: Operations Research Scientist at U. of Phoenix and Apollo Group; Data Mining Consultant/Scientist at BCBST
• Top news, jobs in August - Sep 1, 2011.
  Poll Results: Top Languages for DM/Analytics; Free Stanford courses on AI, ML, DB;
  Top jobs: Statistical Analyst/Data Modeler at Quicken Loans, Detroit, MI; Research Internships at Yandex, Moscow, Russia;
• Additions to KDnuggets in August - Sep 1, 2011.
  New companies, education, meetings, publications, software, solutions, blogs

Courses, Events

• Statistical Modeling Week Workshops, Boston, Oct 17-21 - Sep 13, 2011.
  featuring applications-oriented seminars focusing on the latest trends in statistical analysis. Led by a group of experts in the field, the seminars teach professionals how to apply and understand today's major breakthroughs in statistical methodology.
• Tools for Discovering Patterns in Data, Sep 26-27, Charlottesville - Sep 13, 2011.
  a practical, experience-based, concepts course, which demystifies data mining with clarity and humor. Learn to isolate the essential aspects of a problem and select and combine the right software tools to find useful patterns in noisy, incomplete data.
• Course: Advanced Analytics for the Modern Business Analyst - Sep 12, 2011.
  delivers a unique learning experience that will provide you with the skills to succeed in today's highly analytical and data-driven economy.
• Tableau training, insights - Sep 12, 2011.
  End of Summer sale through September 23 on Tableau courses; top Tableau articles in 2011
• Scaling Up Machine Learning - KDD 2011 Tutorial - Sep 10, 2011.
  a broad view of modern approaches for scaling up machine learning and data mining methods on parallel/distributed platforms from leading researchers at LinkedIn, Microsoft, and Yahoo.
• ACM Data Mining Camp - Oct 15, 2011 - Sep 2, 2011.
  Join Our Unconference/camp and talk about data mining. Registration is required to allow our sponsor to provide refreshements.

Webcasts

• September 28 Webcast: The Analytics Power Lunch for Power Users - Sep 8, 2011.
  see how randomization, bootstrapping, bagging and simulation can be used in significance testing and modeling to balance risk and reduce the impact of model misspecification.

Software

• How to process a million songs in 20 minutes - Sep 8, 2011.
  I show how to use Amazon’s Elastic Map Reduce to determine each song's density (the average number of notes or atomic sounds).
• Frontline Systems buys XLMiner add-in for Excel - Sep 7, 2011.
  XLMiner includes data mining tools such as regression trees, k-nearest neighbors, and neural networks as well as statistics tools like multiple regression, exponential smoothing, and ARIMA models for forecasting.
• 25+ more ways to bring data into R - Sep 5, 2011.
  a large list of free datasets and ways to bring them into R
• Access 100M time series in R in under 60 seconds - Sep 3, 2011.
  DataMarket is a portal with over 14,000 data sets from various public and private sector organizations - more than 100 million time series available for download and analysis.

Jobs

• Business Leader, Fraud Investigation at MasterCard, Purchase, NY or St. Louis, MO - Sep 13, 2011.
  analysis of data to support ad-hoc fraud and payment system integrity reporting requests with a secondary role as backup support for the Fraud Investigation team
• Sr. Statistical Analyst (Digital Media) at Experian Simmons, Deerfield Beach, FL - Sep 9, 2011.
  a computationally-oriented applied statistician who will support the development and production of new products in the digital space.
• Predictive Modeler at Allstate Research/Planning Center (ARPC), Menlo Park, CA - Sep 2, 2011.
  the perfect combination of basic research projects and real business problems, as well as the time, tools and environment to effectively tackle both. We use a variety of modeling tools and algorithms to build sophisticated customer pricing models and gain insight into the causes of insurance claims.
• Manager, Predictive Modeling, Insurance Practice at Big 4 Advisory Services, NYC, Chicago, or Hartford - Sep 1, 2011.
  an experienced consultant to manage predictive modeling engagements for Insurance Industry clients and work with a team to develop a variety of predictive models, including but not limited to: underwriting, pricing, and claims management.
• Sr. SW Development Manager - IR, Web Search, Relevance at Amazon.com, Products Ads Team, Seattle, WA - Sep 1, 2011.
  an online advertising expert to lead our Performance and Optimization team that will contribute research, analytics and engineering expertise for the development of a successful online advertising program.
• Research Statistician-1103205 at Nielsen, Schaumburg, IL - Aug 31, 2011.
  execute and assist in the development of statistical studies and analyses in support of the core business to meet Nielsen client needs.

Academic/Research positions

• Research Assistant Professor in Computer Science and Engineering at U. of Notre Dame, South Bend, IN - Sep 12, 2011.
  Research in graph mining, statistical relational learning, network science (especially heterogeneous and composite networks). Join an exciting, inter-disciplinary research grou
• Lecturer at Monash U., Melbourne, Australia - Sep 10, 2011.
  faculty positions in Machine Learning and other areas of computer science
• PhD Position in Medical Data Mining at Maastricht U., the Netherlands - Sep 3, 2011.
  discovering multiple biomarker panels from heart-patient data using data-mining techniques. The final goal is to predict individual outcome and to define therapy beneficial for individual heart patients.

Competitions

• First CrowdANALYTIX contest concludes successfully - Sep 9, 2011.
  Wine quality prediction drew 150+ participants from more than 15 countries. Jason Capehart was the winner.
• Revolution Analytics Launches "Applications of R in Business" Contest - Sep 7, 2011.
  $20,000 in Prizes for users solving business problems with R

Meetings

• PAW NYC Early Bird Ends Friday - PAW-Gov Is Next Week - Sep 8, 2011.
  Predictive Analytics World and Text Analytics World; October 16-21 in New York City
• KDD 2011 Conference -- Days 2/3/4 Summary - Sep 4, 2011.
  I am summarizing all of the days together since each talk was short. By far the most enjoyable and interesting aspects of the conference were the breakout sessions.

Publications

• 6 companies doing big data in the cloud - Sep 9, 2011.
  Cloud computing and big data analytics are a match made in heaven. Several companies have already melded the two into a variety of unique services.
• Top KDD references from the last 4 years - Sep 6, 2011.
  Gabor Melli analysis of KDD conference papers and what were most common citations.
• SAS vs R discussion - Sep 6, 2011.
  one of the big differences between SAS and R is the size of the data sets each can accommodate. Out of the box, that size is limited by physical memory in R, while SAS, with virtual memory management, theoretically has no limits.
• Data scientist: The hot new gig in tech - Sep 6, 2011.
  Companies that want to make sense of all their bits are hiring so-called data scientists - if they can find any.
• Free ebook: Big Data Now - Sep 2, 2011.
  covers data-related content published on O'Reilly Radar over the last year. Mike Loukides kicked things off in June 2010 with "What is data science?" and from there we've pursued the various threads and themes that naturally emerged.
• Study: Most firms say business analytics boosts decision-making process - Sep 2, 2011.
  Most enterprises seek solutions to big issues with business analytics, per Bloomberg Businessweek survey sponsored by SAS
• Lies, damn lies and data mining algorithms - Aug 31, 2011.
  excessive use of data mining can undermine the entire industry; Segmenting risk in insurance eventually destroys the possibility to spread risk equitably. Similar danger exists in other industries.

News Briefs

• IBM Earmarks $1 Billion For SMB Tech - Sep 12, 2011.
  financing will cover analytics and other IBM products/services for SMBs, including cloud, security, collaboration, and storage.
• IBM to buy Algorithmics risk analytics software firm for $387 million - Sep 7, 2011.
  Algorithmics risk analytics software, content and advisory services are used by banking, investment and insurance businesses
• Kelley Blue Book picks SAS Analytics, turns big data into big value - Sep 7, 2011.
  SAS forecasts ad inventory, site traffic and behavior patterns - analytical insights fuel automotive marketplace
• IBM Builds Biggest Data Drive Ever - Sep 5, 2011.
  The 120 petabyte drive could enable detailed simulations of real-world phenomena or store 24 billion MP3s. It is made of 200,000 conventional hard disk drives working together.
• Deloitte Launches Collaborative Online Community for Business Analytics - Sep 5, 2011.
  a social media website for industry insiders to offer analytic insights, share knowledge and best practices, and problem resolution.
• IBM buys i2 for Crime, Fraud Analytics Expertise - Sep 1, 2011.
  i2 is a maker of intelligence analytics tools for crime and fraud prevention

CFP - Calls for Papers

• BigLearn-11: NIPS-2011 Workshop on Big Learning: Algorithms, Systems, and Tools for Learning at Scale, due Sep 30
• SDM12-WT: SDM-12 Workshops/Tutorials proposals, due Sep 30
• SDM12: The Twelfth SIAM Int. Conf. on Data Mining, due Oct 14
• DEEPL-11: Deep Learning and Unsupervised Feature Learning Workshop, due Oct 14
• COSTNIPS: Computational Trade-offs in Statistical Learning, due Oct 17
• FLAIRS-2012-DM: FLAIRS-2012 Special Track on Data Mining, due Nov 21

Quote

Dilbert on What to do when data is wrong