DSC 433/533, Information Analysis for Managerial Decisions

DSC 433/533, Fall 2008

Information Analysis for Managerial Decisions

[ Assignments | Data | Software | News and Handouts]

Course Description: Information Analysis for Managerial Decisions, is a regular course offered by the Department of Decision Sciences in the Lundquist College of Business at the University of Oregon. Data mining and statistical analysis has been widely used to support managerial decision-making. Large collections of structured data (e.g., databases and spreadsheets) may contain implicit patterns or knowledge that cannot be easily detected. However, managers must learn how to leverage this information to make profitable business decisions. Over time, firms rely increasingly upon fact-based decision making approaches, requiring that managers understand how to develop defensible business proposals based on both spreadsheet and database analysis. This course examines the business case for the use of data-driven analytical tools, especially data mining, for enhancing decision-making and managing risk. Data Mining emerged as an interesting research topic since 1980s and has made great strides during the 1990s. It also has got many successful applications in industry and business. In this course, we will study methods for statistics-based data preprocessing, association rule mining, decision tree, neural network, clustering and outlier analysis. By understanding and applying appropriate business models and data mining techniques, we will investigate the effectiveness of data mining techniques in business applications.
Prerequisite: DSC 330 and DSC 340 (business statistics and information systems) or equivalent; business or accounting major (or MBA/grad student).
Time and Place: Tuesdays and Thursdays at 12:00pm - 1:50pm in 312 Lillis Hall.
Instructor: Dejing Dou from Computer and Information Science, 303 Deschutes, phone 346-4572, email dou@cs.uoregon.edu.
Office hours:
- Dejing Wednesdays 3:30pm - 5:00pm or by appointment (I like to talk with students)
News: Keep an eye on the course news for miscellaneous announcements and handouts.
Evaluation:
- You are expected to attend all class periods; Part of your grade will be based on examples and case-studies that we'll discuss in class.
- The homework will be a combination of written and data experiments.
- The Final Project will be due in parts: Part 1 (project proposal) is due Friday November 28 and Part 2 (final report) on Friday December 12. You can work on it in group or individually. Graduate students in DSC 533 are required to give a presentation on the final week: Tuesday December 9, 8:00am - 10:00am.
The approximate weighting of the work done will be

Class Participation 10%

Homework Assignments 30%

Midterm 30%

Final Project 30%
Texts:
- Text 1: Jiawei Han and Micheline Kamber Data Mining: Concepts and Techniques, Second Edition, Morgan Kaufmann. (see text website.)
Supplemental Reading:
- Text 2: Data Mining Techniques: For Marketing, Sales, and Customer Relationship Management (2004, 2nd edition) by Berry and Linoff (ISBN: 0471470643).

Approximate Syllabus and Lecture Slides

Week of	Chapter	Description and Slides	Events

Sep 29	1	intro to Data Mining and softwares
Oct 6	2, 3	data preprocessing, information gain, data warehouse
Oct 13	4 in Text 2	applications in marketing and CRM
Oct 20	5	Association Mining
Oct 27	6	Decision Tree Classification
Nov 3	6	Bayesian Classification , Neural Network
Nov 10	7	Clustering and Outlier Analysis
Nov 17		Midterm Review	Midterm Thursday, Nov 20
Nov 24	8,9,10	Time Sequences, Stock Market, Graph, Social Network	Final Project Part 1 (project proposal): Friday, Nov 28
Dec 1		Project implementations by students (no lectures)
Dec 8		Project Presentations for Graduate Students Tuesday 8:00am - 10:00am	Final Project Part 2(final report): Friday, Dec 12

Late policy: All assignments are due by 11:59pm of the stated due date, though it is much safer to turn them in at class time. Late papers are subject to a 10% per day penalty. Late assignments will not be accepted once the graded papers are returned or once sample solutions are handed out. It is your responsibility to turn in the assignments on time. Make sure that electronically submitted assignments are actually delivered.
Some useful links for data mining softwares and topics:
- Weka data mining software.
- XLMiner software.
- www.data-miners.com
- www.twocrows.com
- www.thearling.com
- www.kdnuggets.com
- Stanford Computer Science info on neural networks
- PAControl.com info on neural networks
- Data Mining Research Links collected by Prof. Mohammed J. Zaki in RPI.
- RuleQuest research data mining tools.

Class Participation	10%
Homework Assignments	30%
Midterm	30%
Final Project	30%