Ron Kohavi, PhD

About Me

My Linkedin profile (View Full Profile).

Professional activities:

• Emetrics 2007 talk on Controlled Experiments.
• Online Experiments: Lessons Learned, IEEE Computer, Sept 2007.
• Practical Guide to Controlled Experiments on the Web: Listen to Your Customers not to the HiPPO. Appears in KDD 2007.
• ACM Data Mining SIG talk (PPT) (June 14, 2006)
• PKDD/ECML 2005 keynote Focus the Mining Beacon: Lessons and Challenges from the World of E-Commerce based on the Machine Learning journal paper.
• General Chair for KDD 2004
  
• Talk at Emetrics 2004 on Amazon's Data Mining and Personalization in PDF (June 2004)
• Co-chair of the WEBKDD'2003, Web mining as a Premise to Effective and Intelligent Web Applications with Bing Liu, Brij Masand, Jaideep Srivastava, and Osmar R. Zaïane 
• Talk at CSLI's Seminar on Computational Learning and Adaptation on Real-world Insights from Mining Retail E-Commerce Data, May 22, 2003
• Article for CACM on Emerging Trends in Business Analytics, Communications of the ACM, Volume 45, Number 8, Aug 2002, pages 45-48. PDF
• Talk at the Etail CRM Summit, 2002.  PDF slides.  The talk was cited in ComputerWorld.
• Talk at KDD 2001 industrial track: paper, and talk
• Talk at SAS's M 2001, Oct 2-3, 2001
• Co-chair of the WEBKDD'2001 workshop: Mining Log Data Across All Customer TouchPoints with Brij Masand, Myra Spiliopoulou,  and Jaideep Srivastava.  Papers available as lecture notes from Springer as a book on Amazon.com.
  
• Talk at PAKDD 2001, April 16-18, 2001. Coverage in the South China Morning Press, the largest English newspaper in Hong Kong.
• Tutorial on E-commerce and Clickstream Mining with Jon Becher at the first SIAM International Conference on Data Mining. Apr 5, 2001.  Tutorial slides and vendor slides.
• Co-editor of a special issue of the International Journal Data Mining and Knowledge Discovery on E-commerce and Data Mining (Feb 2001).  This special issue is also available as a book from Kluwer Academic Publishers at Amazon.com
• Co-chair KDD-CUP 2000 with Carla Brodley.  Press release about this. Coverage in Database Trends.  SIGKDD article.
• Co-chair of the WEBKDD'2000 workshop: Web Mining for E-Commerce with Myra Spiliopoulou and Jaideep Srivastava. Best papers appeared in a special issue of the Data Mining and Knowledge Discovery journal.
• Talk at the National Academy of Engineering, US Frontiers of Engineers, Sept 2000. PDF and Compressed postscript.
• Co-chair KDD-99's industrial track with Jim Gray.
• Co-editor (with Foster Provost) the special issue on Applications of Machine Learning and the Knowledge Discovery Process for the journal Machine Learning.
• Co-chaired a panel with Mehran Sahami at KDD-99 on Integrating Data Mining into Vertical Solutions: Problems and Challenges. The panel summary appeared in SigKDD Explorations Volume 1, issue 2
• Served on MySimon's Technical Advisory Board until they were bought by CNET.

The papers Irrelevant Features and the Subset Selection Problem and Wrappers for Feature Subset Selection are in the top-10 most cited papers in Artificial Intelligence Expert Systems and Machine Learning according to NEC's ResearchIndex. Bias Plus Variance Decomposition for Zero-One Loss Functions and Mining using MLC++, a Machine Learning Library in C++ are in the top-100 most cited papers in Machine Learning.

Full list of publications

Prior to joining Microsoft in June 2005, Ronny was the director of data mining and personalization at Amazon.com, where he was responsible for personalization, automation, search engine marketing (SEM), consumer behavior / data mining, site experimentation, and automated e-mail. His teams introduced several features estimated to be worth several hundred million dollars in incremental revenue. Prior to Amazon, Ronny was the Vice President of Business Intelligence at Blue Martini Software, where he led the engineering group responsible for the data collection, analysis, visualization, reporting, and campaign management modules in Blue Martini's applications. Prior to joining Blue Martini, Kohavi managed the MineSet product, Silicon Graphics' award-winning product for data mining and visualization. Ronny joined Silicon Graphics after getting a Ph.D. in Machine Learning from Stanford University, where he led the MLC++ project, the Machine Learning library in C++ used in MineSet and at Blue Martini Software.  Kohavi received his BA from the Technion, Israel.  He was the General Chair for KDD 2004.  He co-chaired KDD 99's industrial track with Jim Gray and the KDD Cup 2000 with Carla Brodley.  He was an invited speaker at the National Academy of Engineering in 2000, a keynote speaker at PAKDD 2001,  and an invited speaker at KDD 2001's industrial track.  He co-chaired WEBKDD 2000, WEBKDD 2001, and WEBKDD 2003, and co-taught with Jon Becher a tutorial on e-commerce and clickstream mining at the SIAM Data Mining conference in 2001.  He co-edited with Foster Provost the special issue of the journal Machine Learning on Applications of Machine Learning and the special issue of the Data Mining and Knowledge Discovery journal on Applications of Data Mining to Electronic Commerce, now available as a book.  He was a member of the editorial board for the Data Mining and Knowledge Discovery journal from its inception and served as a member of the editorial board for the journal of Machine Learning from 1997 to 1999.

1. Decision Tree. This is a great example where decision trees with many nodes can be visualized effectively. The visualizer was based on SGI's file system navigator, shown in the Jurassic Park movie
2. Evidence Visualizer (aka Naive Bayes). This is an example of how to make conditional probabilities easier to understand. Working in log space, they add up so the concept of "evidence" is easy to understand.
3. Decision Table classifier is simple yet effective and is easy to visualize.
4. Splat Visualizer allows visualizing large amounts of data by creating Gaussian splats
5. Scatter VisualizerVisualizing scatterplots with sliders for a total of 7 dimensions: X, Y, Z, color, size, and two sliders