Commercial Applications of
Machine Learning and Data Mining

TUTORIAL CONTENT

To familiarize Silicon Valley business with the commercial potential of machine learning and data mining, this set of tutorials will examine a variety of application areas, review problems that arise therein, and report case studies in which machine learning has led to their solution. Some general lessons that hold across different applications will also be presented.

Tutorials on machine learning are often organized around classes of techniques, such as neural networks, rule induction, case-based learning, and probabilistic methods. In contrast, these tutorials will be organized around problems areas that arise in the business world. These include detecting regularities in customer records, extracting content from online documents, using interaction traces to personalize online services, and learning usage patterns to detect fraud.

These tutorials will be given by acknowledged experts in the problem areas. Each presentation will include time for a question-answer session, and the series will end with a panel to let the audience ask questions that cross different application areas.

FINAL SCHEDULE

TARGET AUDIENCE

INSTRUCTORS

• Dr. Scott Bennett is Vice President and Director of Research and Development at SRA International. He has worked on the design, development, and deployment of knowledge discovery solutions for government and commercial clients. Dr. Bennett's data mining experience includes work with very large structured and unstructured data sets, parallel architectures for data mining, a variety of discovery and detection algorithms, and graphical tools for analysis of mining results. He worked closely with NASDAQ in architecting and developing the Advanced Detection System (ADS) which uses a combination of discovery and detection algorithms to surveil the market. He is also actively working on applying data mining for intrusion and misuse detection in the computer security area. Dr. Bennett received his PhD from the University of Illinois at Urbana-Champaign in 1993 in the area of machine learning.

• Dr. Pat Langley directs the Computational Learning Laboratory at Stanford's Center for the Study of Language and Information; he also heads the Adaptive Systems Group at the DaimlerChrysler Research and Technology Center and serves as President of MindShadow, a company that applies machine learning technology to construct user profiles from behavioral traces. Dr. Langley received his PhD from Carnegie Mellon University in 1979; he is the author of the textbook "Elements of Machine Learning" (Morgan Kaufmann, 1995), and he is the program chair for ICML-2000. His research has addressed many topics within the field, including computational discovery and adaptive user interfaces.

• Dr. Tom Mitchell is the Fredkin Professor of AI and Machine Learning at Carnegie Mellon University and is founding Director of CMU's Center for Automated Learning and Discovery. He is currently on leave from his university position to serve as Vice President and Chief Scientist at WhizBang! Labs, an internet startup company that employs machine learning to extract information from the web (see www.whizbang.com). Mitchell is author of the textbook "Machine Learning," McGraw Hill, 1997, incoming President of the American Association for Artificial Intelligence, and a member of the National Research Council's Computer Science and Telecommunications board.

• Dr. Andrew Moore is Associate Professor of Robotics and Computer Science at Carnegie Mellon University. He received his PhD in Computer Science from the University of Cambridge in 1991, and he has applied machine learning to robotics, factory control, and supply chain management. He is the co-owner and Chief Technical Officer of Schenley Park Research, Inc., a Pittsburgh startup that supplies data mining and decision theory solutions to manufacturing, business-to-business, and biotechnology clients.

• Dr. Mehran Sahami is Senior Engineering Manager at E.piphany, where he leads their research and development effort in data mining. He also heads the Digital Marketplaces product group at E.piphany. Prior to joining E.piphany, Dr. Sahami was involved in a number of machine learning and data mining research projects at Xerox PARC, SRI International, and Microsoft Research. He received his PhD on the topic of probabilistic approaches to text learning from Stanford University in 1998, where he still teaches on occassion.

LOCATION

REGISTRATION

To register for the tutorials, please fill out the online registration form whether you are paying electronically, by facsimile, or by physical mail. To register by mail, please print out a hard copy of the completed form and send it, with a personal or traveler's check made out to Stanford University, to:

ICML-2000 Tutorials / CSLI
Computational Learning Laboratory
Ventura Hall, Stanford University
Stanford, CA 94305 USA

Return to the web page for the Seventeenth International Conference on Machine Learning.