STATS 415 - Data Mining and Statistical Learning
Section: 001
Term: WN 2009
Subject: Statistics (STATS)
Department: LSA Statistics
Requirements & Distribution:
Waitlist Capacity:
Advisory Prerequisites:
MATH 215 and 217, and one of STATS 401, 406, 412 or 426.
This course counts toward the 60 credits of math/science required for a Bachelor of Science degree.
May not be repeated for credit.
Primary Instructor:

This course covers the principles of data mining, exploratory analysis and visualization of complex data sets, and predictive modeling, Topics include: a) techniques and algorithms for exploratory data analysis and for discovering associations, patterns, changes, and anomalies in large data sets; and b) modern methods for multivariate analysis and statistical learning in regression, classification, and clustering. The presentation balances statistical concepts (such as model bias and over-fitting data, and interpreting results) and computational issues (including algorithmic complexity and strategies for efficient implementation). Students are exposed to algorithms, computations, and hands-on data analysis in weekly discussion sessions.

Intended audience: Course can be used as an elective to satisfy the requirements of the statistics concentration, the applied statistics minor, and the statistics minor.

Course Requirements: Evaluation will be based on weekly problem sets, one midterm exam, and a final project. The final project will be an individual project involving either data analysis using the methods covered in the course, or a simulation-based or analytical investigation of the properties of one of the methods covered in the course. Students will be expected to write a statement of their findings of approximately 3 pages in length, as well as providing clean and documented versions of their computer code,

Class Format: 3 hours of lecture and 1 hour GSI-led discussion.

STATS 415 - Data Mining and Statistical Learning
Schedule Listing
001 (LEC)
10STATS (Maj or Min)
MW 11:30AM - 1:00PM
002 (DIS)
F 10:00AM - 11:00AM
NOTE: Data maintained by department in Wolverine Access. If no textbooks are listed below, check with the department.

ISBN: 9780262082907
Principles of data mining, Author: David J. Hand, Heikki Mannila, Publisher: MIT Press 2000
ISBN: 9781558609013
Data mining : concepts and techniques, Author: Jiawei Han; Micheline Kamber., Publisher: Elsevier/Morgan Kaufmann 2nd ed. 2006
Syllabi are available to current LSA students. IMPORTANT: These syllabi are provided to give students a general idea about the courses, as offered by LSA departments and programs in prior academic terms. The syllabi do not necessarily reflect the assignments, sequence of course materials, and/or course expectations that the faculty and departments/programs have for these same courses in the current and/or future terms.

Click the button below to view historical syllabi for STATS 415 (UM login required)

View Historical Syllabi
The CourseProfile (ART) system, supported by the U-M Provost’s 3rd Century Initiative through a grant to the Digital Innovation Greenhouse, provides additional information about: course enrollments; academic terms and instructors; student academic profiles (school/college, majors), and previous, concurrent, and subsequent course enrollments.

CourseProfile (ART)