KDnuggets™ News 12:n27, Nov 28

Features (6) | Software (4) | Courses, Events (2) | Webcasts (6) | Meetings (3) | Jobs (6) | Academic (4) | Competitions (2) | Publications (6) | NewsBriefs (1) | CFP (5) | Quote

Features

• New Poll: Where did you apply Analytics / Data Mining in 2012? ( comments) - Nov 26, 2012.
  The top 5 industries with most analytics / data mining applications in 2011 were CRM, Banking, Health care/HR, Education, and Fraud detection.
• Statistics2013: The International Year of Statistics - Nov 25, 2012.
  Statistics2013 will promote the importance of Statistics to the broader scientific community, business and government data users, the media, policy makers, employers, students, and the general public.
• PAW: Predictive Analytics World returns to Toronto, Mar 18-21 2013 - Nov 27, 2012.
  Predictive Analytics World (PAW) is the only conference in Canada that offers a unparalleled perspective on analytics where both technical and business knowledge are integrated towards solving real-life business problems. Register by Dec 7 for a super Early Bird.
• IEG: Predictive Analytics Innovation in San Diego, Feb 20-21 - Nov 21, 2012.
  The Predictive Analytics Innovation Summit, San Diego, February 20-21, 2013 is the perfect opportunity to share insight and best practices with the industry's most forward-thinking analytics executives. Get an early pass until Dec 23.
• Top news for Nov 18-24: Best Python modules for data mining; SAP Visual Intelligence Ultimate Challenge - Nov 25, 2012.
  Best Python modules for data mining; Top news for Nov 11-17; Responsibility for Predictions; Understanding PCA
  Top jobs: Manager Data Mining, RnD, StubHub; Data Scientist at Datascope Analytics
• Top news for Nov 11-17: Best Python modules for data mining; Responsibility for Predictions - Nov 18, 2012.
  Best Python modules for data mining; Nate Silver gets Gold on correct election predictions;
  Top jobs: Postdoc, Bayesian Inference/ML at Ohio State; Imaging Scientist at Aware

Software

• IBM: Analyzing Survey Text: A Brief Overview - Nov 27, 2012.
  Researchers can easily get more insight from their text responses using new tools for text analysis - spending less time on manual coding and reaping increased cost savings. See how you can gain a more detailed understanding of your survey results. Download now.
• QDA Miner Lite - Free Version - Nov 27, 2012.
  An easy-to-use tool for coding, annotating and analyzing collections of documents and images such as interview or focus-group transcripts, journal articles, web pages, or customer feedback.
• Predixion data mining workbench free for developers - Nov 23, 2012.
  From the team that brought you the data mining add-ins for Microsoft Office, Predixion Enterprise Insight Developer Edition is now available, on-premise or in the cloud, and it is free - no strings attached - for use in your development environment.
• Best Python modules for data mining ( comments) - Nov 14, 2012.
  best python modules for machine learning, data mining, natural language processing, network analysis, and web scraping

Courses, Events

• TMA Courses in Data Analytics [Feb: Orlando, Apr: Vegas] - Nov 27, 2012.
  Get up to speed in data mining faster and more effectively than with any other training program available. Next courses in Orlando and Las Vegas.
• Business Analytics using Data Mining - Online Course - Nov 17, 2012.
  The course covers data mining techniques and their use in strategic business decision making. Taught by Galit Shmueli, the course is also offered online starting Nov 20. Reg by Dec 1.

Webcasts

• WCAI Research Opportunity: Satisfaction in Repeat Retail Transactions, Dec 6 - Nov 16, 2012.
  This unique data includes employee surveys at Hertz in the US and Canada, transactions of rental cars in those locations, and customer satisfaction surveys for those transactions. Research proposals encouraged to understand the interplay of employee engagement, customer satisfaction, and customer purchase behavior. Register for Dec 6 webinar.
• Skytree Webinar: Choosing the Right Machine Learning Methods, Dec 12 - Nov 27, 2012.
  Dr Alexander Gray, Skytree CTO will present the Skytree approach tor selecting methods and choose several of your problems to discuss as part of the webinar. Submit your big data problems after you register.
• Webinar: Data Mining: Failure to Launch [Dec 12] - Nov 27, 2012.
  Learn how to get started with predictive modeling and overcome strategic and tactical limitations that cause data mining projects to fall short of their potential.
• IBM Webinar, Dec 13: Use the past to predict the future - Nov 19, 2012.
  Predictive analytics software can help you unlock hidden insights and use all of your data to drive better outcomes throughout your organization. Learn more in upcoming IBM webinar.
• Salford Webinar, Dec 14: Advances in Gradient Boosting: the Power of Post-Processing - Nov 22, 2012.
  Covering Gradient Boosting and Post-Processing, Applications benefiting from Post-Processing: industry examples, Typical Post-Processing Steps and Techniques.
• StatSoft Webinar (Dec 18): Predicting Sales Using STATISTICA Uplift Modeling - Nov 21, 2012.
  Uplift modeling comes into play when predictive analytics is implemented within your organization's marketing/sales strategy. So, how do you measure effectiveness?

Meetings

• NII Shonan Informatics Meetings - Call for Proposals - Nov 21, 2012.
  NII Shonan meetings follow the Dagstuhl model to promote informatics and informatics research by providing a premier venue for world-class scientists, young researchers, and practitioners to come together in Asia.
• Oracle BIWA Summit: Jan 8-10, Redwood City, CA - Nov 20, 2012.
  The Oracle BIWA Summit brings together Oracle ACE experts, customers who are currently using or planning to use Oracle BI, Warehousing and Analytics products and technologies, partners and Oracle Product Managers, Support Personnel and Development Managers.
• EGC 2013 Toulouse: Call for Participation - Nov 16, 2012.
  This French-speaking international conference is devoted to theories, methods and applications of data mining, machine learning, knowledge discovery in databases, knowledge management and engineering.

Jobs

• Senior Scientist, Knowledge Discovery, Data Mining at Firmenich, Geneva, Switzerland - Nov 27, 2012.
  Complete the existing knowledge science team and undertake data mining activities related to perfumes and flavors. Firmenich is the largest privately-owned company in the perfume and flavor business and created many of the world's favorite perfumes for over 100 years.
• Intuit: Staff Software Engineer, Data Driven New Business Initiatives at Intuit, Mountain View, CA - Nov 22, 2012.
  You'll have the opportunity to work alongside world-class scientists, gain insight into cutting edge data-mining and machine learning techniques and implement complex distributed algorithms to create insight and value from Intuit's large-scale data assets.
• Manager Data Mining, RnD StubHub at StubHub, part of ebay, San Francisco, CA - Nov 18, 2012.
  Responsible for managing team of data mining engineers, DW and BI reporting engineers to develop the next generation of BI, Analytics and data mining solutions here at StubHub
• Data Scientist at Datascope Analytics, Chicago, IL - Nov 17, 2012.
  Love analyzing and visualizing data to solve important problems; wants to improve and teach others, and is fun to be around and work with. Apply by Dec 2.
• Director of Analytics at A9 (part of Amazon.com), Palo Alto, CA - Nov 16, 2012.
  An experienced technical leader to provide data-driven analyses of Amazon product search, improving the user search experience, and managing the search infrastructure.
• Data Scientist/Statistician at Deloitte, Singapore - Nov 14, 2012.
  The Institute goal is increase Deloitte market eminence across industry domains through Analytics, and achieve differentiation by bringing research to life and into the heart of business.

Academic/Research positions

• Postdoc/Visiting Faculty in Bioinformatics at Connecticut College, New London, CT - Nov 27, 2012.
  Help developing a center for collaborative research and teaching in the intersection of computer science and biology
• Faculty, AI, Machine Learning, Data Mining at IMT Lucca, Italy - Nov 23, 2012.
  Institute is seeking to strengthen its core research activities in the analysis and management of complex technological, socio-economic, and natural systems, especially big-data, large-scale, and dynamical. Apply by Dec 31.
• Herman Goldstine Memorial Postdoc Fellowship at IBM, Yorktown Heights, NY - Nov 16, 2012.
  Areas of active research include: algorithms, complex systems, data mining, dynamical systems, high-performance computing, inverse problems, numerical analysis, optimization, probability theory, statistics, simulation and operations management.
• Asst. Prof. in Database Systems, Data Mining at Northwestern U., Evanston, IL - Nov 15, 2012.
  Particular focus on areas such as large-scale data management, integration of structured and unstructured data, parallel and distributed data mining and analytics, stream databases, and database engines for scalable computing and emerging computer architectures.

Competitions

• CrowdAnalytix Contest: Holiday Sales Forecasting - Nov 23, 2012.
  This contest will challenge solvers to forecast sales for the entire holiday season - Nov, Dec, and Jan at a monthly level.
• SAP Visual Intelligence Ultimate Data Geek Challenge - deadline Nov 30 - Nov 19, 2012.
  Grab your data and share your visual creation in a video, screen capture, or blog post on the SAP Community Network (SCN). Once you enter, you'll have a chance to be crowned the Ultimate Data Geek.

Publications

• Understanding Principal Component Analysis - Nov 24, 2012.
  PCA is a good technique to reduce the high dimensionality of big data sets to fewer dimensions that are easier for humans to comprehend and visualize.
• National Journal: Drones and Data Mining - After the Election ( comments) - Nov 19, 2012.
  The conventional wisdom has been that the "air war" - the amount of advertising on TV and Radio matters more than the "ground war" - the size of the volunteer pool, said Charles Duhigg. Now the conventional wisdom is that most important factor is the size of the volunteer base.
• Top KDnuggets tweets, Nov 12-14: Best Python modules for data mining; Why Data Science is hard to teach in college - Nov 15, 2012.
  Best Python 2.7 modules for data mining; Why Data Science is hard to teach in college - @mathbabe explains; A Moneyball-style revolution for VCs - algorithm to predicts startup success?; Impressive BigData partnership: Google BigQuery and Tableau visualization
• Top KDnuggets tweets, Nov 15-18: pandas: Powerful data analysis tool for Python; Useful BigData trends and stats - Nov 19, 2012.
  pandas: Powerful data analysis tool for Python - code and slides - awesome; Useful Big Data trends and stats; MIT researchers algorithm compresses #BigData on the fly for much faster processing; Beware the Big Data Campaign - how much did data mining help win the election?
• Top KDnuggets tweets, Nov 19-21: Ajay Ohri on Excel, best R packages, and how R is viewed; The Human Face of Big Data - a preview of the book - Nov 22, 2012.
  Ajay Ohri on Excel, best R packages, and whether R is viewed as a threat; The Human Face of #BigData - a preview of the book, with unexpected photos; Mind-blowing Idea: Free transportation for life, if you buy Tesla S electric car; If Data is the new oil, don't end up being BP - 3 key concepts to avoid a disaster
• Top KDnuggets tweets, Nov 22-25: A contrarian view of data scientists and Kaggle; Successes of Deep Learning - Nov 26, 2012.
  A contrarian view of what data scientists do and why Kaggle is wrong; Successes of Deep Learning (using machine learning w. neural networks); The Big Data fallacy, and why with more data useful information is harder to find; Interactive Data Visualization for the Web (with D3) - an interactive O'Reilly book

News Briefs

• Connotate Survey: Enterprise Perceptions on the Value of Big Data - Nov 15, 2012.
  Enterprises are moving forward with Big Data initiatives, despite the lack of clear definition of Big Data, and lack of proof whether most Big Data projects are delivering ROI.

CFP - Calls for Papers

• RFID: RFID: towards Ubiquitous Computing & the web of Things, due Nov 30
• DMMH-13: Data Mining for Medicine and Healthcare, due Jan 7
• CARR-12: 3rd Workshop on Context-awareness in Retrieval and Recommendation, due Feb 5
• UMUAI: User Modeling and User-Adapted Interaction, due Mar 1
• VBI 2013: Visualisation and Business Intelligence, due Mar 1

Quote

As Jean-Jacques Rousseau put it, "a little bit of agitation gives motivation to the soul, and what really makes the species prosper is not peace so much as freedom." With freedom comes some unpredictable fluctuation. This is one of life's packages: there is no freedom without noise - and no stability without volatility.

Nassim Nicholas Taleb and Mark Blyth in the Black Swan of Cairo: How Suppressing Volatility Makes the World Less Predictable and More Dangerous (Thanks to Ismail Parsa for the quotation)