Weigend Stat252 Stanford Data Mining and E-Business

Andreas S. WEIGEND, Ph.D.

Office Location: Sequoia 127
Office Hours: MTW 2:15-3:00pm

Stat252
Summer 2004
Stanford University

Class Location: Skilling 193
Class Time: MTW 3:15-5:00pm

Date	Topic	Guest Speakers
T 6/29	Introduction: Measurement, Modeling, Prediction, and Action	-
W 6/30	Personalization: When, When Not, and What Then Instead?	-
T 7/6	Market Research: Creating Information Products from Behavioral Data	-
W 7/7	Design of Experiments: Short-term vs Long-term Effects	Selden Crary (President of WebDOE.com)
M 7/12	Web Search: Past, Present and Future	Jan Pedersen (Chief Scientist/Search of Yahoo)
T 7/13	Mining Music: What to do with Moodlogic's 1 Billion Music Ratings Recommender Systems: What Works and What Doesn't	Chris Pirkner (EVP Corporate Development and Co-founder of Moodlogic) Jon Herlocker (Assistant Prof, Oregon State University; Co-founder of NetPerceptions)
W 7/14	Midterm	-
M 7/19	The eBay Customer Lifecycle: IT and Analytics	Jim Oliver (Director of Database Marketing at eBay)
T 7/20	What Happened to the Infomediary?	John Hagel (johnhagel.com)
W 7/21	Technical Review (by TAs)	-
M 7/26	Probabilistic Models for Filtering Spam	Rick Giarrusso (CEO of Angenous; Founder of Data Digest)
T 7/27	Creating Information Products for Wall Street Class followed by reception sponsored by Majestic Research	Seth Goldstein (CEO of Majestic Research)
W 7/28	*	TBA
T 8/3	Predicting Company Valuation from Customer Behavior Presentations of Best Course Projects	Bernd Skiera (Prof, Johann Wolfgang Goethe-Universität Frankfurt) Students

*Other Topics:

Social Network Analysis: Discovering Opinion Leaders and Building Community
Predicting and Influencing Conversion (from browsing to buying, from free registration to paid subscription)
Optimizing Online Advertising and Keyword Arbitrage
Digital Goods and E-Business Strategy
Comparison Shopping and Behavioral Economics
People Search: Understanding Customer Behavior on Online Dating Sites (or: What people really want...)

Grading:

25% Midterm. No notes, closed book.
10%: 5 thoughtful questions by 7/19 2pm on: The Coming Battle for Customer Information (J.Hagel, J.F Rayport, 1997; HBR), and Unbundling the Corporation. (J.Hagel, M. Singer, 2000; HBR)
40% Group Project. Do see TAs early!
25% Participation. Remote students to send in summaries before noon of day of subsequent class.

Readings:

Required textbooks
- BL: M.J.A. Berry and G.S. Linoff: Data Mining Techniques (2nd edition, 2004) (pdf) Applications of data mining in marketing and sales
- BFS: P. Baldi, P. Frasconi, and P. Smyth (2003) Background on Web technology, statistical modeling of behavior, information retrieval

Recommended textbooks
- DHS: R.O. Duda, P.E. Hart, D.G. Stork: Pattern Classification (2nd edition, 2000) Data analysis (great collection of many useful techniques)
- SV: C. Shapiro, H.R. Varian: Information Rules (1998) E-Business strategy (network effects, economics of digital goods, pricing, etc.)

Teaching Assistants:

TA for students taking the course in the classroom:
- Armin Schwartzman
  Office hours: Mon and Tue 2:15 – 3:00pm, Sequoia 238,or by appointment via email
  armins@stanford.edu
TA for students taking course remotely, and students who prefer communicating through e-mail:
- Eric Bair
  ebair@stanford.edu

http://www.weigend.com/Teaching/Stanford/index.html
by

| +1 (917) 697-3800 | www.weigend.com