KDnuggets™ News 11:n27, Nov 9

Features

• Poll Results: Top Algorithms for Analytics/Data Mining - Nov 8, 2011.
  Latest KDnuggets Poll shows that Decision Trees, Regression, and Clustering are the top algorithms; Uplift modeling has the highest industry affinity. Only 14% have used Cloud analytics so far.
• Kaggle gets Venture Funding - Nov 3, 2011.
  Kaggle, a platform for data mining competitions, got $11 million from investors including Khosla Ventures, Index Ventures, PayPal co-founder Max Levchin, and Hal Varian, Google's chief economist.
• IEEE ICDM Research Contributions Award - Nov 7, 2011.
  the winner is Prof. Geoff McLachlan (U. of Queensland) for many contributions to the fields of classification, statistical learning, and pattern recognition.
• IEEE ICDM Outstanding Service Award - Nov 7, 2011.
  the winner is Dr. Christopher Clifton (Purdue University), recognized for a long history of promoting ICDM and the data mining field in general.
• PAW London Coming Nov 30 - Dec 1 - Nov 5, 2011.
  Delivering case studies, leading speakers, and a featured workshop on Predictive Modeling Methods with John Elder.
• Top news for Oct 30 - Nov 5 - Nov 6, 2011.
  R Cookbook with examples; More Frequently-Asked Questions (and Answers);
  Top jobs: Manager, Client Analytics at Edward Jones, St. Louis; Analytics Manager at Opera Solutions, Paris.

Courses, Events

• Learn What Really Works in Data Mining: Dec in LA, Feb in Atlanta, Apr in Vegas - Nov 8, 2011.
  insist on 1000% ROI from your data mining initiatives! Learn how to get it from TMA Predictive Analytics and Data Mining course series.

Webcasts

• Webcast and Research Opportunity: Cultivating Disaster Donors - Nov 7, 2011.
  The challenge to researchers is: 1) develop analytical tools for identifying likely repeat donors amongst those who first contribute to a disaster and 2) determine which marketing strategies are most effective in transitioning these donors from disaster-based to long-term.

Software

• Investigative Analytics Startup from Cloudera Founder - Nov 6, 2011.
  WibiData will help manage and analyze complex business data about users, and can be used for personalization for e-commerce and gaming. Wibidata is built on Apache Hadoop and HBase.
• Pentaho Announces Extreme Scale In-Memory Analytics - Nov 3, 2011.
  This release provides the benefits of an in-memory solution without the limitations of an in-memory only architecture.

Jobs

• Ruby on Rails Developer (Analytics) at In-Q-Tel, Arlington, VA - Nov 7, 2011.
  design and development of proof of concepts that demonstrate next generation techniques for extracting value from data such as Anomaly Detection, Discovery, Search, Affinity, or Inference.
• Traffic Quality Forensic Engineer at Microsoft, Redmond, WA - Nov 5, 2011.
  Does investigating invalid search traffic, click issues, detecting click fraud, and supporting Analytics tools sound exciting to you? Do you have advanced SQL or Excel skills and a passion for delivering an excellent customer experience?
• Manager Software Development 2 at eBay Inc., San Jose, CA - Nov 5, 2011.
  manage Seller Standards team; lead and grow a world class engineering team in a dynamic, fast paced & collaborative environment.
• Staff Scientist (energy intelligence) at FirstFuel Software, Waltham, MA - Nov 4, 2011.
  FirstFuel Software is the energy intelligence company that helps Utilities engage their commercial customers and rapidly achieve energy efficiency across commercial building portfolios.
• Herman Goldstine Memorial Postdoc Fellowship at IBM, Yorktown Heights, NY - Nov 3, 2011.
  The fellowship provides scientists of outstanding ability an opportunity to advance their scholarship as resident department members at the Research Center.
• Analytics Manager at Opera Solutions, Paris, France - Nov 3, 2011.
  Opera Solutions is the largest independent predictive analytics company in the world, providing Big Data Analytics as an ongoing service to blue-chip clients across the globe.

Academic/Research positions

• Postdoc/PhD positions on Context-Aware Predictive Analytics at TU Eindhoven, Netherlands - Nov 2, 2011.
  Postdoc and PhD positions in the field of data mining, knowledge discovery and web analytics in the STW (Dutch Technology Foundation) funded project "Context Awareness in Predictive Analytics" (CAPA).

Competitions

• WSDM Yandex Relevance Prediction Challenge - Nov 8, 2011.
  The challenge provides a fully anonymized dataset from Yandex, with user queries, clicks on URLs and their relevance labels.
• Competition: Photo Quality Prediction - Nov 6, 2011.
  Using anonymized photo albums, predict if a human evaluator would mark them as good.

Meetings

• Salford Analytics and Data Mining Conference Registration Now Online - Nov 8, 2011.
  Registration for the Salford Analytics and Data Mining Conference (San Diego, May 24-25) and pre-conference training is at http://bit.ly/rpRC2r . Conference will feature top experts and practitioners.

Publications

• On data mining reputation and the ethics of data collection - Nov 4, 2011.
  Solon Barocas, a PhD student at NYU, a speaker at Strata conference, discussed the perceptions of data mining and how companies can address data mining's reputation.
• On Big Data: Interview with Dr. Werner Vogels, CTO and VP of Amazon.com - Nov 2, 2011.
  In the new world of data analysis your questions are going to evolve and change over time and as such you need to be able to collect, store and analyze data without being constrained by resources.
• More Frequently-Asked Questions (and Answers) about Data Mining - Nov 2, 2011.
  Tim Graettinger answers: How much data do I need for data mining? Why doesn't my predictive model perform as well on new data as it does on the training data? and more.

News Briefs

• Alpine Miner for Oracle - Nov 4, 2011.
  Alpine Miner Version 2.0 for Oracle is available for Oracle 11g and Oracle Exadata Database Machine, and includes support for all data analytics operations, and more.
• IDC names 2011 Innovative Business Analytics Companies Under $100M to Watch - Nov 4, 2011.
  New IDC report highlights 6 companies which exemplify one or more key trends: Collaborative Decision Management, Cloud-based Analytics, Mobile Analytics.

CFP - Calls for Papers

• TMW12: Text Mining Workshop, due Jan 13
• KDD-12W: KDD-2012 Workshop Proposals, due Jan 15
• KDD-2012: 18th ACM SIGKDD Conf. on Knowledge Discovery and Data Mining, due Feb 10
• INFN-12: Information Fusion, Data Mining, and Knowledge Discovery in Hybrid Networks, due Apr 6

Quote

Mark Zuckerberg