Ronny Kohavi's publications

Comm ACM on data mining

My Ph.D. thesis in compressed postscript or acrobat (PDF): Wrappers for Performance Enhancement and Oblivious Decision Graphs.

Note: publications below are in reverse chronological order, i.e., the most recent ones are first.

Even though I am not in academia since 1995, my articles have been cited over 1,000 times according to NEC's ResearchIndex and I am in the list of Most cited authors in Computer Science
 

  1. Ronny Kohavi, Emetrics talk on Controlled Experiments, Oct 2007.
  2. Ronny Kohavi and Roger Longbotham, Online Experiments: Lessons Learned, IEEE Computer, Sept 2007.
  3. Ronny Kohavi, Randy Henne, and Dan Sommerfield, Practical Guide to Controlled Experiments on the Web: Listen to Your Customers not to the HiPPO, KDD 2007.
  4. Ron Kohavi, ACM Data Mining SIG talk (PPT) (June 14, 2006)
  5. Ron Kohavi, PKDD/ECML 2005 keynote Focus the Mining Beacon: Lessons and Challenges from the World of E-Commerce based on the Machine Learning journal paper
  6. Ron Kohavi, talk at Emetrics 2004 on Amazon's Data Mining and Personalization in PDF (June 2004)
  7. Ron Kohavi, Llew Mason, Rajesh Parekh, Zijian Zheng, Lessons and Challenges from Mining Retail E-Commerce Data. PDF.
    To appear in Machine Learning Journal, Special Issue on Data Mining Lessons Learned, 2004.
  8. Ron Kohavi and Rajesh Parekh, Visualizing RFM Segmentation, SIAM International Conference on Data Mining, (SDM) 2004. PDF
  9. Ron Kohavi and Rajesh Parekh, Ten Supplementary Analyses to Improve E-commerce Web Sites, WEBKDD 2003.  PDF
  10. Talk at CSLI's Seminar on Computational Learning and Adaptation on Real-world Insights from Mining Retail E-Commerce Data, May 22, 2003
  11. Deriving Key Insights from Blue Martini Business Intelligence: Summary of key insights from using Business Intelligence against Debenhams and MEC sites. Approved by Debenhams and MEC and presented at Webinar on March 10, 2003.  PPT
  12. Blue Martini Software, Bath Unlimited Tests Product Acceptance with Blue Martini's Online Market Research Capabilities. PDF
  13. Blue Martini Software, Blue Martini Business Intelligence Delivers Unparalleled Insight into User Behavior at the Debenhams Web Site  PDF
  14. Blue Martini Software, Blue Martini Business Intelligence at Work: Charting the Terrains of MEC Website Data.  PDF
  15. Ron Kohavi, Neal Rothleder, and Evangelos Simoudis, Emerging Trends in Business Analytics, Communications of the ACM, Volume 45, Number 8, Aug 2002, pages 45-48. PDF
  16. Ron Kohavi, Mining Customer Data, Etail CRM Summit, 2002.  PDF slides.  The talk was cited in ComputerWorld.
  17. Ron Kohavi and J. Ross Quinlan.  Decision-tree discovery.  In Will Klosgen and Jan M. Zytkow, editors, Handbook of Data Mining and Knowledge Discovery, chapter 16.1.3, pages 267-276. Oxford University Press, 2002.  Postscript, PDF.
  18. Nir Friedman and Ron Kohavi. Bayesian classification. In Will Klosgen and Jan M. Zytkow, editors, Handbook of Data Mining and Knowledge Discovery, chapter 16.1.5, pages 282-288. Oxford University Press, 2002.  Postscript, PDF.
  19. Cliff Brunk and Ron Kohavi.  Mineset.  In Will Klosgen and Jan M. Zytkow, editors, Handbook of Data Mining and Knowledge Discovery, chapter 24.2.4, pages 584-589. Oxford University Press, 2002.  Postscript, PDF.
  20. Ron Kohavi and Dan Sommerfield. MLC++. In Will Klosgen and Jan M. Zytkow, editors, Handbook of Data Mining and Knowledge Discovery,  chapter 24.1.2, pages 548-553. Oxford University Press, 2002. Postscript, PDF.
  21. Ron Kohavi, Brij Masand, Myra Spiliopoulou, and Jaideep Srivastava, Lecture Notes in Artificial Intelligence (no 2356): WEBKDD 2001 - Mining Log Data Across All Customer Touch Points, Revised papers, Third International Workshop, San Francisco, CA, Aug 2001.    Original papers available here.
  22. Llew Mason, Zijian Zheng, Ron Kohavi, Brian Frasca, eMetrics Study, Dec 2001.  PDF
  23. Zijian Zheng, Ron Kohavi, and Llew Mason, Real World Performance of Association Rule Algorithms, KDD 2001, short, long, slides.  One of the datastes used in this paper (BMS-WebView-1) was donated for research use under similar terms to the KDD Cup 2000 data usage.  See link at the bottom of http://www.ecn.purdue.edu/KDDCUP/
  24. Suhail Ansari, Ron Kohavi, Llew Mason, and Zijian Zheng, Integrating E-Commerce and Data Mining: Architecture and Challenges, ICDM 2001, PDF
  25. Ron Kohavi Invited paper/talk at KDD 2001 industrial track: Mining E-commerce Data, the Good, the Bad, and the Ugly PDF paper, slides
  26. Ron Kohavi,  Mining E-commerce Data, the Good, the Bad, and the Ugly, invited talk at PAKDD 2001, April 16-18, 2001, Hong Kong.
    Coverage in the South China Morning Press, the largest English newspaper in Hong Kong.
  27. Ron Kohavi and Foster Provost, Applications of Data Mining to Electronic Commerce, Data Mining and Knowledge Discovery journal 5(1/2), 2001. Postscript, PDF
    This special issue is also available as a hardcover book from Kluwer Academic Publishers; ISBN: 0792373030
  28. Ron Kohavi, Carla Brodley, Brian Frasca, Llew Mason, and Zijian Zheng, KDD-Cup 2000 Organizers' Report:  Peeling the Onion.  SIGKDD Explorations Volume 2, issue 2, 2000.  PDF
    Also translated to Japanese in Information Processing Society of Japan, Vol 42 No. 5
  29. Myra Spiliopoulou, Jaideep Srivastava, Ron Kohavi, and Brij Masand, WEBKDD 2000 - Web Mining for E-Commerce, SIGKDD Explorations Volume 2, issue 2, 2000.  PDF
  30. Ron Kohavi, An Ideal E-Commerce Architecture for Building Web Sites Supporting Analysis and Personalization. Invited talk at the Information Architecture and Web Site Design class, Berkeley, Oct 2000.  PDF
  31. Ron Kohavi, Mining E-Commerce Data: The Good, the Bad, and the Ugly.  Invited talk at the SAS's M2000 Data Mining Technology conference, Oct 2000.  PDF and Compressed postscript
  32. Ron Kohavi, Data Mining and Visualization. Invited talk at the National Academy of Engineering US Frontiers of Engineers, Sept 2000. PDF and Compressed postscript.  Available in book form ISBN: 0-309-07319-7
  33. Ron Kohavi, Personalization Panel, KDD conference, Aug 2000. Powepoint slides
  34. Ron Kohavi and Carla Brodley, KDD-Cup 2000: Peeling the Onion. Talk at KDD 2000. Powerpoint slides
  35. Suhail Ansari, Ron Kohavi, Llew Mason, and Zijian Zheng, Integrating E-commerce and Data Mining: Architecture and Challenges, WEBKDD'2000 workshop on Web Mining for E-Commerce -- Challenges and Opportunities, Aug 2000. PDF and Compressed postscript
  36. Ron Kohavi, Mining E-Commerce Data: Challenges and Stories from the Trenches. DIMACS/IBM Workshop on Data Mining in the Internet Age, 2 May 2000. HTML slides and Compressed postscript
  37. Ron Kohavi and Mehran Sahami (co-chairs), Jim Bozik, Dorian Pyle, Rob Gerritsen, Steve Belcher, Ken Ono (panelists). Integrating Data Mining into Vertical Solutions: Problems and Challenges, KDD-99 panel ZIP'ed slides and article in SigKDD Explorations Volume 1, issue 2
  38. Ron Kohavi, Embedding Data Mining Technology in E-Commerce Applications. Invited talk at ICML-99 industrial day. June 99, Slovenia. ZIP'ed powerpoint slides and HTML slides.
  39. Eric Bauer and Ron Kohavi, An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants, Journal of Machine Learning Vol 36, Nos. 1/2, July/August 1999, pages 105-139 compressed postscript (632K) updated 5/22 /99 or acrobat (PDF).
  40. Ron Kohavi and George John, The Wrapper Approach, book chapter in Feature Extraction, Construction and Selection : A Data Mining Perspective, edited by Huan Liu and Hiroshi Motoda.  Postscript
  41. Ron Kohavi, Improving Accuracy by voting Classification Algorithms: Boosting, Bagging, and Variants. Invited talk at Workshop on Computation-Intensive Machine Learning Techniques. Australia, Sept 1998 compressed postscript slides
  42. Ron Kohavi and Foster Provost, Glossary of Terms. Editorial for the Special Issue on Applications of Machine Learning and the Knowledge Discovery Process (volume 30, Number 2/3, February/March 1998). Postscript or HTML
  43. Ron Kohavi and Foster Provost, On Applied Research in Machine Learning. Editorial for the Special Issue on Applications of Machine Learning and the Knowledge Discovery Process (volume 30, Number 2/3, February/March 1998). Postscript
  44. Ron Kohavi, Crossing the Chasm: From Academic Machine Learning to Commercial Data Mining. Invited talk at ICML-98. compressed postscript slides or acrobat (PDF) slides
  45. Afshin Goodarzi, Ron Kohavi, Richard Harmon, and Aydin Senkut, Loan Prepayment Modeling. Appeared in KDD-98 workshop on Data Mining in Finance. high-res compressed postscript or lower-res acrobat (PDF)
  46. Ron Kohavi, Data Mining with MineSet: What Worked, What Did Not, and What Might. Appeared in KDD-98 workshop on the Commercial Success of Data Mining. compressed postscript or acrobat (PDF)
  47. Ron Kohavi and Dan Sommerfield, Targeting Business Users with Decision Table Classifiers. Appeared in KDD-98. compressed postscript or acrobat (PDF)
  48. Ron Kohavi, Technique Selection in Machine Learning Applications. Invited talk at the ICML-98 workshop on the Methodology of Applying Machine Learning. compressed postscript slides or acrobat (PDF) slides
  49. Foster Provost, Tom Fawcett, Ron Kohavi, Building the Case Against Accuracy Estimation for Comparing Induction Algorithms. ICML-98. compressed postscript or (low-res) acrobat (PDF)
  50. Jeff Bradford, Clay Kunz, Ron Kohavi, Cliff Brunk, and Carla Brodley, Pruning Decision Trees with Misclassification Costs.  ECML-98. compressed postscript and long version in compressed postscript
  51. Ron Kohavi, Dan Sommerfield, and James Dougherty, Data Mining using MLC++, a Machine Learning Library in C++. International Journal of Artificial Intelligence Tools, Vol. 6, No. 4, 1997, p. 537-566. This is a longer version of the TAI'96 paper that received the IEEE Tools With Artificial Intelligence Best Paper Award. compressed postscript (283K) or acrobat (PDF)
  52. Barry Becker, Ron Kohavi, Dan Sommerfield, Visualizing the Simple Bayesian Classifier. Appears in the KDD 1997 Workshop on Issues in the Integration of Data Mining and Data Visualization. Lecture Notes in Computer Science by Springer Verlag. compressed postscript (358K).
  53. Cliff Brunk, James Kelly, and Ron Kohavi, MineSet: An Integrated System for Data Mining. Appears in the The Third International Conference on Knowledge Discovery and Data Mining, 1997. compressed postscript (276K).
  54. Ron Kohavi and Clayton Kunz, Option Decision Trees with Majority Votes. Apears in the International Conference on Machine Learning 1997. postscript (308K).
  55. Ron Kohavi and George John, Wrappers for Feature Subset Selection (late draft). In Artificial Intelligence journal, special issue on relevance, Vol. 97, Nos 1-2, pp. 273-324.NEC's ResearchIndex one of the top referenced paper in Machine Learning. Compressed postscript (305K) uncompressed postscript (770K)
  56. Ron Kohavi, Barry Becker, and Dan Sommerfield, Improving Simple Bayes compressed postscript. ECML-97 (poster).
  57. Ron Kohavi, Pat Langley, Yeogirl Yun, The Utility of Feature Weighting in Nearest-Neighbor Algorithms compressed postscript. ECML-97 (poster).
  58. Ron Kohavi, MLC++ Developments: Data Mining using MLC++. AAAI Fall Symposium on Learning Complex Behaviors in Adaptive Intelligent Systems, Nov 1996. compressed postscript slides.
  59. Ron Kohavi, Dan Sommerfield, and James Dougherty, Data Mining using MLC++, a Machine Learning Library in C++. TAI 96. The paper received the IEEE Tools With Artificial Intelligence Best Paper Award, 1996.  NEC's ResearchIndex one of the top referenced paper in Machine Learning.  Compressed postscript (245K) or uncompressed postscript (3.3MB)
  60. Ron Kohavi and Mehran Sahami, Error-Based and Entropy-Based Discretization of Continuous Features. KDD-96. postscript (165K)
  61. Ron Kohavi, Scaling Up the Accuracy of Naive-Bayes Classifiers: a Decision-Tree Hybrid. KDD-96. compressed postscript (108K) or slides.
  62. Ron Kohavi, Book Review: Empirical Methods in Artificial Intelligence by Paul Cohen. International Journal of Neural Systems (IJNS), Vol 7, No 2, May 1996, p. 219-221. postscript. (50K) Note: final formatting in the journal was slightly different
  63. Ron Kohavi and David Wolpert, Bias Plus Variance Decomposition for Zero-One Loss Functions. ML96.  NEC's ResearchIndex one of the top referenced paper in Machine Learning. PDF or postscript (170K) or color slides for 2/7/96 talk (390K) (18 slides. ghostview doesn't work well on these. Use xpsview).
  64. Jerome Friedman, Ron Kohavi, and Yeogirl Yun, Lazy Decision Trees. AAAI-96, p. 717-724. postscript(145K) or slides.
  65. Ron Kohavi and Dan Sommerfield, Feature Subset Selection Using the Wrapper Model: Overfitting and Dynamic Search Space Topology. KDD-95. postscript (240K) or slides.
  66. Ron Kohavi and George John, Automatic Parameter Selection by Minimizing Estimated Error. ML-95. postscript (173K).
  67. James Dougherty, Ron Kohavi, and Mehran Sahami, Supervised and unsupervised discretization of continuous features. ML-95. postscript (213K) or slides.
  68. Ron Kohavi, A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. IJCAI-95. postscript (305K), PDF , or slides.
  69. Ron Kohavi and Chia-Hsin Li, Oblivious Decision Trees, Graphs, and Top-Down Pruning. IJCAI-95 postscript (171K).
  70. Ron Kohavi, The Power of Decision Tables. In the European Conference on Machine Learning, 1995. postscript (168K) or slides with some new results on discretization.
  71. Ron Kohavi and Brian Frasca, Useful feature subsets and rough set reducts. In the International Workshop on Rough Sets and Soft Computing (RSSC), 1994. postscript version (161K).
  72. Ron Kohavi, A third dimension to rough sets. In the International Workshop on Rough Sets and Soft Computing (RSSC), 1994. postscript version (163K).
  73. Ron Kohavi, Feature Subset Selection as Search with Probabilistic Estimates. In the AAAI Fall Symposium on Relevance, 1994. postscript version (126K).
  74. Ron Kohavi, George John, Richard Long, David Manley, and Karl Pfleger, MLC++:A Machine Learning Library in C++. In Tools with Artificial Intelligence, 1994. postscript version (118K).
  75. Ron Kohavi, Bottom-up induction of oblivious, read-once decision graphs : Strengths and limitations. In Twelfth National Conference on Artificial Intelligence, 1994. postscript version (199K).
  76. George John, Ron Kohavi, and Karl Pfleger, Irrelevant features and the subset selection problem. In Machine Learning: Proceedings of the Eleventh International Conference, 1994. Morgan Kaufmann. postscript (224K) or slides.
  77. Ron Kohavi, Bottom-up induction of oblivious, read-once decision graphs. In Proceedings of the European Conference on Machine Learning, 1994. postscript version (211K).
  78. Ron Kohavi and Scott Benson., Research note on decision lists. Journal of Machine Learning. 13(1), 1993
  79. Ron Kohavi and Yoav Shoham, Applications of datalog theories in AI. In AAAI-92 Workshop on Tractable Reasoning. 82-87
My home page
ronnyk@CS.Stanford.edu