KDnuggets™ News 10:n28, Dec 1

Features (4) | Webcasts (1) | Software (1) | Jobs (14) | Academic (1) | AudioVideo (1) | Publications (8) | NewsBriefs (4) | CFP (4) | Quote

Features

• Tim Berners Lee: Social Networks are a threat to the Web - Nov 28, 2010.
  Large social-networking sites are walling off information posted by their users from the rest of the web
• New Poll: "Do not track" registry vs ad targeting - Nov 22, 2010.
  US Congress is currently discussing "Do not track registry", which will allow people to opt-out of tracking. Do you think such registry, if enacted, will significantly reduce ad targeting and behavioral advertising?
• New in KDnuggets in November - Nov 30, 2010.
  Additions to KDnuggets in Companies, Meetings, Publications, Software sections
• Most viewed items for Nov 21-27 - Nov 29, 2010.
  Google Refine cleans up data; Online book: Intro to data mining;
  Top jobs: Math Modeling and Optimization at ExxonMobil Research, Clinton, NJ; Relevance scientist / Research programmer at Yandex Labs, Palo Alto, CA;

Webcasts (see also All Webcasts)

• Webinar, Dec 1: Intro to Bayesian networks and BayesiaLab - Nov 30, 2010.
  We will provide an introduction on how to use Bayesian networks and Probabilistic Structural Equation Models for market research.

Software (see also All Software)

• ANGOSS Releases Knowledge Seeker Version 7.5 - Nov 26, 2010.
  Numerous usability enhancements in this release have been generated from the Angoss user community

Jobs (see also All Jobs)

• Analytics Manager at Opera Solutions, London, UK and Paris, France - Nov 29, 2010.
  Opera Solutions is a new generation consulting firm that melds the best of human intelligence and powerful, technology-driven tools into a unique approach that delivers rapid and significant profit improvement to our clients.
• Research Engineer (Ranking) at Chomp, San Francisco, CA - Nov 26, 2010.
  Chomp is an app discovery product that helps users find the best mobile apps. Lead research and development of the scoring/ranking component of the Chomp search engine
• Software Engineer (Data Mining/Machine Learning) at Chomp, San Francisco, CA - Nov 26, 2010.
  Chomp is an app discovery product that helps users find the best mobile apps. Own design and development of the recommendation engine at Chomp; Learn about state of the art research; Plan algorithmic improvements and produce production quality code.
• Quantitative Modeling Consultants at Agilex Technologies, Alexandria, VA - Nov 24, 2010.
  support government programs; be a self-starter with demonstrated experience using SAS and SQL programming
• Sr. Software Development Engineers at Agilex Technologies, Alexandria, VA - Nov 24, 2010.
  support government programs; be a self-starter with demonstrated experience using machine learning to develop algorithms and enterprise systems to perform network based search and text extraction through entity resolution using structured and unstructured data
• Senior Engineers, Architect and Fresh College Grads at Rocket Fuel, Redwood City, CA - Nov 24, 2010.
  we are bringing rocket science to online display advertising. Hiring fresh college grads, sr engineers and architects to build and enhance ad-serving, bidding and data infrastructure built using a mix of proprietary and open-source technologies.
• Relevance scientist / Research programmer at Yandex Labs, Palo Alto, CA - Nov 24, 2010.
  research scientist position in Web relevance group; A graduate degree in IR, machine learning or a related field, hands on in UNIX/code dev, and contribute to research, experimentation and development in Web search quality.
• Software Engineer at Yandex Labs, Palo Alto, CA - Nov 24, 2010.
  Work on Yandex Search Quality. We look for motivated and driven individual contributors with experience in C++, Python, Perl development and distributed high-performance systems
• Scientist at ID Analytics, San Diego, CA - Nov 24, 2010.
  participate in developing advanced technologies, like statistical score modeling, score model development, score model deployment, large scale database analysis and statistical algorithms.
• Senior Software Engineer at Yandex Labs, Palo Alto, CA - Nov 24, 2010.
  To work on Yandex Search Quality; experienced and motivated individual contributors, experts with C++, Python, Perl, and distributed high-performance systems
• Software Engineer - Crawler at Chomp, San Francisco, CA - Nov 23, 2010.
  Own the design and development of the Chomp crawler. Chomp is an app discovery product that helps users find the best mobile apps.
• Research Engineer - Search at Chomp, San Francisco, CA - Nov 23, 2010.
  Lead research and development of the scoring/ranking component of the Chomp social app discovery engine to help people find the apps they need.
• Research Engineer- Natural Language Processing at Chomp, San Francisco, CA - Nov 23, 2010.
  Chomp is an app discovery product that helps users find the best mobile apps. Research Engineer will use natural language processing techniques to preprocess data for input into Chomp's search engine; stay aware of state of the art research
• Software Development Engineer, Community Content - RCX at Amazon.com, Seattle, WA - Nov 23, 2010.
  Does the prospect of using machine learning techniques at scale excite you? Would you like to work on one of the world's largest corpora of customer-provided content? Are you an incredibly strong software engineer?

Academic/Research positions

• Faculty, All Levels (Tenured, Tenure-Track, Lecturer, Visiting) at U. of Iowa, Dept. of Management Sciences, Iowa City, Iowa - Nov 23, 2010.
  Areas of interest include but are not limited to database, machine learning, data and text mining, web search, and knowledge management.

Audio/Video

• Lies, damned lies and statistics (about TEDTalks) - Nov 26, 2010.
  This brilliant and funny statistical analysis of past TED Talks offers a method for creating both the best and worst TEDTalk

Publications

• Predicting stock price movements - INFORMS Contest Results - Nov 29, 2010.
  Predict stock price direction in next 60 minutes. With almost 900 participants, the winning entry had AUC of 0.99.
• Decisions That Drive Success white paper - Nov 30, 2010.
  Read this white paper to learn how decision management makes it possible to use predictive analytics as an integral part of real-time decision process
• New book: Data Analysis with Open Source Tools - Nov 30, 2010.
  With this insightful book, intermediate to experienced programmers interested in data analysis will learn techniques for working with data in a business environment.
• JSM 2011 Student Paper Competition, due Jan 28 - Nov 30, 2010.
  The paper might be an original methodological research or analysis of data (from various fields including but not limited to pharmaceutical, genomics, bioinformatics, imaging, defense, business, public health) that uses principles and methods in statistical learning and data mining.
• How wise are crowds? - Nov 24, 2010.
  By melding economics and engineering, researchers show that as social networks get larger, they usually get better at sorting fact from fiction.
• Running Kaggle Chess Ratings Contest - Nov 24, 2010.
  The major challenge is that chess ratings are longitudinal (results from earlier tournaments can be used to predict later tournaments).
• New Book: Business Analytics for Managers - Nov 24, 2010.
  presents a sustainable business analytics (BA) model focusing on the interaction of IT technology, strategy, business processes, and a broad spectrum of human competencies and organizational circumstances.
• Online book: Introduction to data mining - Nov 23, 2010.
  this online book was created by the Data Mining group at the U. Toronto, and it covers all steps of data mining process, from problem definition, data preparation, exploration, to modeling, evaluation, and deployment.

News Briefs

• Vermont Data Mining Law Is Ruled Unconstitutional - Nov 28, 2010.
  A federal appeals court has ruled that a Vermont law restricting data mining of prescription drug info is unconstitutional
• Italian agency to use Teradata and SAS to stop healthcare fraud - Nov 29, 2010.
  Italy's social security agency (INPS) wants to detect the noncompliant behaviors in terms of prognosis accuracy, whether by companies or individual claimants.
• Computers Key to Fighting Medicare Fraud - Nov 28, 2010.
  Geographic information systems and other technologies offer new hope for reducing government health-care fraud
• Google Instant Page Previews Wreaking Havoc On Web Analytics - Nov 24, 2010.
  an instant preview on the Google search results sometimes can result in Google "on-demand" fetch of the page, which can cause inflations in your visits, page views, increase in bounce rates, conversion drops, etc.

CFP - Calls for Papers (see also All CFP)

• SDM 2011 Workshop on Text Mining , due Jan 14
• SDM 2011 Workshop on Parallel Data Mining, due Jan 14
• KDD-2011: Knowledge Discovery and Data Mining Workshop proposals, due Feb 1
• KDD-2011: Knowledge Discovery and Data Mining, due Feb 11

Quote

ohnosecond ~ n. The time it takes to realize that you've just goofed by doing something dumb or absentminded on a computer, e.g., forgetting to attach a document to an email.

from wordsyoudontknow.com