KDnuggets™ News 10:n07, Apr 7

Features

• New Poll: Will you buy the Apple iPad? - Apr 6, 2010.
  Please vote on www.kdnuggets.com
• Poll Results: Anonymization Still Possible - Apr 6, 2010.
  Majority of responders thought it was still possible for companies to anonymize and release large personal datasets, but some questioned if the anonymized data would still be useful.
• Data Mining, Analytic Blog Highlights - Apr 6, 2010.
  Data Mining Consultant with Egg on Face; Predictive Analytics and Politics; Asking questions of your social network
• Most viewed items for week Mar 28 - Apr 3 - Apr 5, 2010.
  PAKDD 2010: Data Mining Competition; KDD Cup 2010: Educational Data Mining. Top Jobs: Data Analyst at Blizzard Entertainment; Predictive Modeler/Data Mining Analyst at Humana.
• Innocentive 100K Challenge: Predictive DNA Data Analysis - Apr 2, 2010.
  a $100,000 prize is offered for a best solution for a problem related to DNA analysis and predicting traits in the test set.
• Google changes its name to Topeka - Apr 1, 2010.
  We didn't reach this decision lightly; after all, we had a fair amount of brand equity tied up in our old name.
• PAKDD 2010: Data Mining Competition - Mar 29, 2010.
  How to build a model for a binary decision support system based on this type of biased sample in a credit scoring application
• Most viewed items for week Mar 21-27 - Mar 28, 2010.
  News: New Poll: Is anonymization of large datasets still possible? KDD Cup 2010: Educational Data Mining.
  Jobs: Analytics Engineer at Eventbrite; Data Mining Engineer at eBay
• KDD Cup 2010: Educational Data Mining - Mar 23, 2010.
  This year's challenge asks you to predict student performance on mathematical problems from logs of student interaction with Intelligent Tutoring Systems.
• KDD-2010 Workshops - calls for papers - Mar 22, 2010.
  KDD-2010 will have 4 full day workshops: Mining and Learning with Graphs; Large-scale Data Mining; Useful Patterns; Social Media Analytics; and 5 half day ones: KDD Cup 2010; BIOKDD10; MDMKDD 2010; ADKDD'10; Human Computation

Webcasts (see also All Webcasts)

• SAS Webinar, Apr 21: Text Analytics 101 - Apr 5, 2010.
  practical, accessible advice about how to seamlessly incorporate text-based insights for better decisions (free SAS Webinar)

Software (see also All Software)

• ECML/PKDD Discovery Challenge 2010: Web Content quality - Apr 6, 2010.
  The goal is to develop automatic site-level classifiers including aspects such as trustworthiness, authoritativeness, neutrality, and genre (editorial, news, commercial, educational, Web spam and more).
• TunedIT: on-line student competition platform - Apr 2, 2010.
  TunedIT on-line data mining and machine learning competition platform is now open for teachers who want to organize on-line student contests
• Get the Data Mining Add-ins made for you - Apr 2, 2010.
  Predixion Software, founded by several ex-Microsoft data miners, is seeking your feedback on data mining add-ins and components
• DEiXTo: a free, DOM based, web data extraction tool - Mar 30, 2010.
  a powerful tool for creating "extraction rules" (wrappers) that describe what pieces of data to scrape from a web page; consists of GUI and a stand-alone extraction rule executor.

Jobs (see also All Jobs)

• Senior Analyst, Hotel Revenue Optimization (11757) at Expedia, Bellevue, WA, USA or Geneva, Switzerland - Apr 2, 2010.
  The Revenue Optimization group is responsible for driving optimal pricing, placement and product recommendations across all of Expedia's brands and domestic and international points of sale
• Software Development Engineer at Amazon.com, Seattle, WA - Apr 1, 2010.
  Product Ads team is looking for exceptional software engineers to develop algorithms and build systems to solve a variety of Information Retrieval, Data Mining, and Distributed Caching problems related to Ad Targeting - one of the company's biggest opportunities for growth.
• Data Analyst at Blizzard Entertainment, Irvine, CA, USA - Mar 31, 2010.
  The ideal candidate will be a good communicator and will have the technical expertise to support projects that require heavy data-crunching and applying statistical and data-mining techniques
• Predictive Modeler/Data Mining Analyst at Humana, Louisville, KY - Mar 30, 2010.
  Are you an analytical thinker? Would you enjoy using your mathematical knowledge to help analyze and improve current business processes and financial metrics?
• Software Development Manager, Catalog Search Experience and Browse at Amazon.com, Seattle, WA, USA - Mar 25, 2010.
  Amazon.com's Fact Extraction (FX) team is looking for a technically strong and charismatic leader to manage a team of software developers tasked with improving the quality of our catalog
• Software Development Engineer at Amazon.com, Seattle, WA, USA - Mar 25, 2010.
  The Fact Extraction (FX) team specializes in processing semi-structured merchant contributions to extract meaningful structured information to augment and correct Amazon's Item Catalog.
• Product Head - Loyalty Analytics at Manthan Systems, Bangalore (India), UK, USA - Mar 25, 2010.
  This role demands entrepreneurial qualities to organically grow this line of business while owning P&L responsibility
• Sr. Statistician/Statistician at American Credit Acceptance, Spartanburg, SC - Mar 24, 2010.
  American Credit Acceptance, a subprime lender for automobile loans, seeks an individual with graduate or post-graduate level education to use statistical analysis and intuition to solve business problems

Academic/Research positions

• Data Mining Intern at WestEd.org, Oakland, CA - Mar 27, 2010.
  we seek an intern to analyze detailed log files, at the mouse click level, of college students using the Virtual Lab to solve problems in stoichiometry and thermodynamics.

Meetings (see also All Meetings)

• New York, Apr 13: Inaugural Sentiment Analysis Symposium - Apr 6, 2010.
  This event bridges technology and business: software that discovers business value in opinions and attitudes in social media, news and enterprise feedback.
• ECML PKDD 2010 Industrial Session - Call For Participation - Apr 1, 2010.
  The session will consist of invited presentations leading industry experts in machine learning and data mining, and a panel on the future research challenges and opportunities

Publications

• Data Mining the University - Apr 6, 2010.
  I began to wonder how students could have trouble with these basic concepts ("Didn't you have to know that for the SAT?"), yet have high GPAs in their major ... we realized the data was actually available to investigate these questions further.
• Forbes: Obama's Data Visionary - Apr 5, 2010.
  Edward Tufte, the guru of data visualization, recently joined the Obama administration Recovery Advisory Panel to help clearly visualize the spending and effects of the $787 billion in recovery stimulus funds. Forbes talked with Tufte about his Sisyphean government project, how companies can apply his lessons to making sense of their ever-swelling stores of data, and his excitement about the iPad.
• Forbes: Data-Driven Companies, a Special Report - Apr 5, 2010.
  A look at the data-driven companies and their technologies, including Why Predictive Analytics Is A Game-Changer; Obama's Data Visionary; Who Is In Charge Of Your Data and more
• Two-by-Two Classification and Decile Tables - A Comparison - Apr 5, 2010.
  I outline how to construct both tables, and pose questions to raise awareness that each approach has its own weakness
• Health Law Demands Patient-Centered Outcomes Research - Apr 5, 2010.
  The Law creates a $500 million Patient-Centered Outcomes Research Institute to study of which drugs, devices and medical procedures work best.
• byoBI: Bring your own BI, structured and unstructured - Mar 31, 2010.
  byoBI is a world of analytical components that are created by a community of interested users. The components of byoI are analytical elements called bidgets.
• SIGEVOlution Volume 4, Issue 4 - Mar 31, 2010.
  featuring * Galactic Arms Race by E. Hastings and K. Stanley; A Perl Primer for EA Practitioners by J. Merelo ...
• KDnuggets Forum Questions - Mar 25, 2010.
  Normalization of Inputs; Hot Topics in Data Mining; Multi-class in Apriori

News Briefs

• LookSmart Appoints Vincent Granville as Chief Scientist - Apr 6, 2010.
  LookSmart, an online search advertising solutions company, announced the appointment of Vincent Granville as Chief Scientist.
• Prescription Data-Mining Case Goes to the First Circuit - Apr 6, 2010.
  drug marketers are successful at influencing physicians' prescribing habits, such as using prescriptions for expensive brand-name drugs instead of generics. Some states are trying to curb this, including limiting access to physician prescribing history.
• Need a Cab? New Analysis Shows Where to Find One - Apr 6, 2010.
  The most popular corners to catch a yellow cab in Manhattan can now be pinpointed, at any hour of any day of the week, thanks to a record of 90 million actual taxi trips that have been silently tracked by the city.
• IDC: a Third of US Organizations Unsure How to Measure Analytics Benefits - Apr 3, 2010.
  Spending intentions for 2010 investments in business analytics solutions are highest in the life sciences and securities and investment industries.
• Jingwei International Reports 2009 Year End Results - Apr 2, 2010.
  a leading provider of data mining and interactive marketing services in China, reported financial results for 2009.
• Insurers Are Missing The Data-Mining Boat, Deloitte Says - Apr 1, 2010.
  Insurers have a wealth of customer information they could employ for product marketing, but lacking data-mining strategies, according to a study from Deloitte
• SeatGeek Predicts the Best Time to Buy Concert and Sports Tickets - Mar 31, 2010.
  SeatGeek is a free, innovative search and forecasting web application that helps users save money on sports and concert tickets.
• Aristotle Political Data-Mining Technology Cleared - Mar 29, 2010.
  Federal Election Commission has voted to take no action on a complaint against Aristotle filed by competitor NGP Software that alleged the company was improperly using Federal Election Commission contributor data
• Number of People Using Advanced Analytics - Mar 27, 2010.
  If traditional BI is far from pervasive in the business world, then advanced analytics is a mere drop in the bucket.
• IBM Unveils New Predictive Analytics Lab in China - Mar 26, 2010.
  The new lab will serve as a global hub for analytics development for industries such as banking, telecommunications, power grid, railroads, health care and urban management
• UK Ministry of Justice Chooses IBM SPSS Predictive Analytics - Mar 26, 2010.
  Turns to Business Analytics to Analyse 4 Million Prisoner Records to Predict the Likelihood of Prisoners Re-Offending
• San Francisco Data Mining Camp Impressions - Mar 25, 2010.
  the unconference - with a new location and almost doubled attendance - was a success - even if judging only by results of twitter sentiment analysis tools

CFP - Calls for Papers (see also All CFP)

• ICDM 2010 Workshop proposals, due Apr 14
• IDEAL 2010: Intelligent Data Engineering and Automated Learning, due Apr 19
• SNA-KDD Workshop: Social Network Mining and Analysis, due Apr 30
• KDD-10 workshop: Discovering, Summarizing and Using Multiple Clustering, due May 4
• KDD-10 workshop: Knowledge Discovery from Sensor Data, due May 4
• KDD-10 workshop: Intelligence and Security Informatics, due May 4
• ICDM'10: IEEE Int. Conference on Data Mining , due May 6
• Manifold Learning, due May 14
• ACML 2010: Asian Conference on Machine Learning, due Jul 12

Quote

Howard Aiken