KDnuggets™ News 11:n30, Dec 14

Features (10) | Courses, Events (3) | Software (3) | Jobs (7) | Academic (2) | Competitions (1) | Publications (6) | NewsBriefs (6) | CFP (13) | Quote

Features

• Top Analytics / Data Mining Stories in 2011 - Dec 13, 2011.
  Free Public Datasets; Analytics/data mining tools used for a real project; Judge forbids use of Bayes Theorem. Really?
  Top jobs: Predictive Modeling/Data Mining Scientists at Obama 2012 Campaign; Data Mining Scientist at Apple.
• Poll Results: Industries where Analytics / Data Mining were applied in 2011 - Dec 12, 2011.
  The most popular industries for analytics were CRM, Banking, Health care, Education, and Fraud detection. The highest growth was in Travel/Hospitality, Social Networks, and Education, and biggest decline in Manufacturing.
• Ventana/KDnuggets Survey on Predictive Analytics - Dec 7, 2011.
  Are you using or considering using predictive analytics to improve future outcomes of your business activities and processes? Participate in the survey with our partner Ventana Research, and you will get a free report with findings.
• The Risks of Using Spreadsheets For Data Analysis - Dec 6, 2011.
  Find out how spreadsheets limitations can be liabilities, and learn about a better way to analyze data. Download IBM white paper "The Risks of Using Spreadsheets for Statistical Analysis".
• Predictive Analytics World March 2012, San Francisco Super Early Bird ends Dec 16 - Dec 13, 2011.
  Predictive Analytics World, March 4-10, 2012, in San Francisco is packed with the top predictive analytics experts, practitioners, authors and business thought leaders.
• Gartner Business Intelligence Summit, Los Angeles, Apr 2-4 - Dec 7, 2011.
  The Gartner BI Summit (LA, Apr 2-4) is the premier business analytics event that provides the must-have insights, frameworks and best practices. Special discount for KDnuggets readers.
• Top news for Dec 4-10 - Dec 11, 2011.
  Growing your own data scientists; The Risks of Using Spreadsheets For Data Analysis; 20% off on new CRC Books on Data Mining, ML
  Top jobs: Decision Scientist at Microsoft; PRINCIPAL (Federal Finance/Analytics) at Booz Allen Hamilton.
• Top news for Nov 27 - Dec 3 - Dec 4, 2011.
  The Search For Analysts To Make Sense Of Big Data; Big Data Gold; Competition: Recognition for Learning
  Top jobs: Data Scientists, Master Data Storyteller at Knewton, NYC.
• Additions to KDnuggets Directory in November - Dec 1, 2011.
  New education, meetings, publications, software
• Top news, jobs in November - Dec 1, 2011.
  Poll Results: Top Algorithms for Analytics/Data Mining; Free Web Mining Services for the People; Google BigQuery
  Top jobs: DM/Research Analyst at Princeton U.; Analytical Modeling Scientist, SAS, San Diego.

Courses, Events

• Online courses on R from statistics.com - Dec 9, 2011.
  Luis Torgo teaches "Data Mining in R", Jan 13 - Feb 10, and Paul Murrell teaches "Introduction to R - Data Handling", Feb 10 - Mar 9
• Tackling Data Overload - Dec 6, 2011.
  Northwestern U. McCormick School of Engineering and Applied Science has developed a new degree program, the Master of Science in Analytics, to teach young professionals the skills they need to succeed in the field.
• Learn What Really Works in Data Mining: Feb in Atlanta, Apr in Vegas - Dec 1, 2011.
  Insist on 1000% ROI from your data mining initiatives! Learn how to achieve it at TMA's Predictive Analytics and Data Mining course series.

Software

• Coron System: a symbolic data-mining platform - Dec 9, 2011.
  Coron is a free data mining toolkit designed for itemset extraction and association rule generation; also provides support for preparing and filtering data, and for interpreting the extracted units of knowledge.
• Alpine Data: the first real data mining solution for the Big Data generation - Dec 3, 2011.
  Alpine Miner is addressing the challenges of the scale and affordability of exploiting Big Data by bringing advanced analytics into the hands of business people, and not only statisticians.
• Ajay Ohri Review of Revolution R 5.0 - Dec 3, 2011.
  academics and researchers can easily get their free copy; v 5.0 solves the R memory problem

Jobs

• Senior Scientific Software Engineer at PayScale, Inc., Seattle, WA - Dec 13, 2011.
  We are the leading source of compensation data on the Internet, powered by innovative search and query algorithms that dynamically acquire, analyze and aggregate compensation information for millions of individuals in real time.
• Analyst II - Survey Research - High Tech at Ingram Micro, Santa Ana, CA - Dec 12, 2011.
  experienced survey researcher with high technology marketing experience; designing surveys, collecting data, data analysis, results generation and results presentations.
• Principal Software Development Engineer at Microsoft Bing, Bellevue, WA - Dec 6, 2011.
  lead the architecture design and development for our Data Platform and Data API. Strong expertise and experience on large scale platform design and development with a track record of shipping multiple releases.
• Sr. Research Software Development Engineer at Microsoft Bing, Bellevue, WA - Dec 6, 2011.
  part of a very strong and fun team building data infrastructure, conducting research and experiments, and developing data mining, machine learning, and BI techniques for solving some of the most challenging problems
• Decision Scientist at Microsoft, Redmond, WA - Dec 6, 2011.
  analyze, optimize and implement computational rules used to monitor and control activity; customer-focused, detail-oriented, results-driven analytic professional with great communication skills and a strong knowledge of DB/statistical techniques; background in the payments and fraud prevention space.
• PRINCIPAL (Federal Finance, Advanced Analytics) at Booz Allen Hamilton, McLean, VA - Dec 5, 2011.
  expand existing, and develop new, business in the Federal Financial Services sector with a focus on Advanced Analytics.
• Sr Business Application Analyst at FedEx Services, Collierville, TN, USA - Dec 5, 2011.
  an excellent opportunity for a candidate with exceptional data analytics capabilities, enthusiasm for the field of predictive analytics and a desire to take your skills to the next level through the application of these skills to solve complex real world problems.

Academic/Research positions

• Post-Doctoral Fellowship at Wharton Customer Analytics Initiative at U. of Pennsylvania, Pennsylvania, PA - Dec 8, 2011.
  The fellowship will be supported by Mars, Inc., who will provide the fellow with rich and unique data sets which will allow the student to explore problems related to social networks, multi-media consumption, purchase timing, and advertising effectiveness.
• Postdoc Position in Social Network Mining and Analysis at Rutgers U., New Brunswick, NJ - Dec 5, 2011.
  research on formation and evolution of roles (i.e. functions of persons) in social networks, development of formal models of roles in social networks and development of efficient algorithms for role detection and dynamics. Start Jan 2.

Competitions

• USPTO $50K Innovation Challenge - Dec 4, 2011.
  The US Patent and Trademark Office, together with the NASA Tournament Lab, is launching a contest to develop new algorithms to aid in patent examination. Register by Dec 5.

Publications

• 20% off on new Chapman and Hall/CRC Books on Data Mining and Machine Learning - Dec 10, 2011.
  Books include "Spectral Feature Selection for Data Mining", "A First Course in Machine Learning", and "Cost-Sensitive Machine Learning".
• Case Study: 1275% Boost in Ability to Identify Churning Customers - Dec 13, 2011.
  Fast-growing mobile telecommunications operator 2degrees increased their ability to identify customers at risk of churning by 1,275% using 11Ants Customer Churn Analyzer
• New Global Study: Only One-Third of Companies Making Effective Use of Data - Dec 12, 2011.
  Largest-Ever Data Science Study Cites Looming Talent Shortage, Lack of Open Data Access as Key Opportunity Inhibitors for Big Data
• Human Brain Is Limiting Global Data Growth ? - Dec 12, 2011.
  Weber discovered that the smallest increase in weight a human can perceive is proportional to the initial mass, and in general relationship between the stimulus and perception is logarithmic. This has a profound effect on the rate at which we absorb information.
• Growing your own data scientists - interviews with leaders in the field - Dec 9, 2011.
  Interviews with leading data scientists from Tableau, LinkedIn, EMC Greenplum, and Amazon on what is a data scientist and how to grow your own.
• Has Consumer Data Mining Gone Too Far? - Dec 2, 2011.
  Privacy advocates say that the collection of data has gone too far, exploiting consumers who have less and less control over how their personal information is doled out. Wharton prof. Peter Fader believes much of the controversy around data collection stems from sloppy marketing.

News Briefs

• IBM Analytics Solution to Extract Insight from Patents, IP - Dec 13, 2011.
  new analytics software and services designed to help companies understand and more effectively use intellectual property, scientific literature and molecular data to advance their business.
• NineSigma seeking Big Data Collection and Analysis System - Dec 7, 2011.
  NineSigma, representing a Fortune 100 Company, is seeking proposals for the development of an innovative system to collect and analyze big data gathered from consumer behaviors.
• Digital Reasoning Raises Venture Financing for Automated Understanding of Big Data - Dec 6, 2011.
  The VC round had participation from In-Q-Tel and partners of Silver Lake. The investment will accelerate development and sales into new Financial Intelligence, Enterprise Risk Management and related markets.
• INFORMS Innovation in Analytics Award - call for applications - Dec 5, 2011.
  the award recognizes creative and unique developments, applications or combinations of analytical techniques; promotes the awareness of the value of analytics techniques in unusual applications, or in creative combination to provide unique insights and/or business value. Submit a brief summary by January 31, 2012.
• DataSift Offers Social Data Analytics Service - Dec 5, 2011.
  DataSift, a child of TweetMeme, adds Lexalytics sentiment analysis, Klout influence scores to social search business.
• HP Combines Autonomy and Vertica for Big Data - Dec 5, 2011.
  New solution pairs the software from HP Autonomy and Vertica acquisitions to analyze and process Big Data.

CFP - Calls for Papers

• IFSUG-12: Insurance and Finance SAS Users Group Summit, due Dec 16
• PMCEC12: Special Session on Process Mining , due Dec 19
• RMBook: RapidMiner book - Call for Chapters, due Dec 31
• ICWSM-12: Weblogs And Social Media, due Jan 13
• MultiClust2012: Discovering, Summarizing and Using Multiple Clusterings, due Jan 13
• DNASDM-12: Workshop on Dynamic Network Analysis, due Jan 13
• PAW Chicago: Predictive Analytics World Chicago, due Jan 19
• KDD-2012: 18th ACM SIGKDD Conf. on Knowledge Discovery and Data Mining, due Feb 10
• PAW Germany: Predictive Analytics World Germany, due Mar 2
• DMIN'12: The 2012 Int. Conf. on Data Mining, due Mar 12
• ECML-PKDD 2012: The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, due Apr 19
• PGM2012: Probabilistic Graphical Models Workshop, due Apr 27
• IMMM 2012: Information Mining and Management, due Jun 7

Quote

Marcelo Gleiser on "Why is Higgs Boson sometimes called the God Particle"?

The God Particle is the title of a popular science book by Nobel Prize winner Leon Lederman, who was Fermilab's director for many years and thus my boss when I was a postdoctoral fellow there. According to Leon, he wanted to call the book The Goddamn Particle because nobody could find the thing. However, his editor discouraged him from the title, suggesting that The God Particle would sell many more copies.

NPR, Dec 12, 2011