CSE 450 Course Plan Notes Summer 2016 Se
Section: F
CSE 450 Course Plan Notes – Summer 2016
Course Instructor: Mohammad Mahmudur Rahman
Grading Plan:
Theory
Final exam
40
Mid-term exam
25
3 Class tests [Spot test]
15
1.
2.
3.
Data Preparation and cleaning
Classification and Prediction
Clustering
Attendance
7
Assignment: 2 (1 on dataset preparation + 1 on data mining)
5
Presentation: 2 (Based on assignment)
8
Total
100
Bonus marks
A) Marks awarded in class
5
B) Performance of a Kaggle contest
5
Activity List
Assignment 1 opens
Class Test 1
3rd week (May 21 – May 27)
Theory
Theory
Classroom
th
Classroom
th
4 week (May 28 - June 3)
Assignment 1 submission and
presentation
Theory
7 week (June 18 - June 24)
Classroom
Mid-term exam
Theory
8th week (June 25 - July 1)
Exam hall
Assignment 2 opens
Class Test 2
Class Test 3
th
Theory
9 week (July 9 – July 15)
Theory
Classroom
th
Classroom
th
Classroom
th
10 week (July 16 – July 22)
Theory
13 week (August 6 – August 12)
Assignment 2 submission and
presentation
Theory
14 week (August 13 – August 19)
Classroom
Final exam
Theory
16th week (August 27 – September
3)
Exam hall
Course Reference Material
Name
Data Mining: Concepts and Techniques, Third
Edition
Author
ISBN-13
Jiawei Han, Micheline Kamber and Jian Pei
978-0123814791
orange.biolab.si/getting-started/
www.kaggle.com
Curriculum Design
Theory
1.
•
•
•
•
Introduction
Course logistics
Overview of data mining tasks
Application examples
2.
•
•
Data Warehousing
Introduction to Orange and Weka
•
•
•
•
•
Data mining processes
Data Cleaning and Dataset preparation
Dividing dataset into training, validation and test sets
Finding ready made dataset
Assignment 1 discussion
3.
4. Association Rule Mining
5. Neural Network
6.
•
•
•
•
Classification and Prediction
Regression
Tree based approaches
Using Neural Network
•
•
Clustering
Assignment 2 discussion
7.
8. CRISP-DM
9.
•
•
Time Series Mining
Mining Data Streams
•
•
Multi-Relational Data Mining
Data Mining for Fraud Detection
•
•
Introduction to Recommender System
Collaborative filtering
•
•
•
•
Data Mining Applications in real life
Research problems
Practicing in Kaggle
Tools and libraries
10.
11.
12.
13. Review and way forward
CSE 450 Course Plan Notes – Summer 2016
Course Instructor: Mohammad Mahmudur Rahman
Grading Plan:
Theory
Final exam
40
Mid-term exam
25
3 Class tests [Spot test]
15
1.
2.
3.
Data Preparation and cleaning
Classification and Prediction
Clustering
Attendance
7
Assignment: 2 (1 on dataset preparation + 1 on data mining)
5
Presentation: 2 (Based on assignment)
8
Total
100
Bonus marks
A) Marks awarded in class
5
B) Performance of a Kaggle contest
5
Activity List
Assignment 1 opens
Class Test 1
3rd week (May 21 – May 27)
Theory
Theory
Classroom
th
Classroom
th
4 week (May 28 - June 3)
Assignment 1 submission and
presentation
Theory
7 week (June 18 - June 24)
Classroom
Mid-term exam
Theory
8th week (June 25 - July 1)
Exam hall
Assignment 2 opens
Class Test 2
Class Test 3
th
Theory
9 week (July 9 – July 15)
Theory
Classroom
th
Classroom
th
Classroom
th
10 week (July 16 – July 22)
Theory
13 week (August 6 – August 12)
Assignment 2 submission and
presentation
Theory
14 week (August 13 – August 19)
Classroom
Final exam
Theory
16th week (August 27 – September
3)
Exam hall
Course Reference Material
Name
Data Mining: Concepts and Techniques, Third
Edition
Author
ISBN-13
Jiawei Han, Micheline Kamber and Jian Pei
978-0123814791
orange.biolab.si/getting-started/
www.kaggle.com
Curriculum Design
Theory
1.
•
•
•
•
Introduction
Course logistics
Overview of data mining tasks
Application examples
2.
•
•
Data Warehousing
Introduction to Orange and Weka
•
•
•
•
•
Data mining processes
Data Cleaning and Dataset preparation
Dividing dataset into training, validation and test sets
Finding ready made dataset
Assignment 1 discussion
3.
4. Association Rule Mining
5. Neural Network
6.
•
•
•
•
Classification and Prediction
Regression
Tree based approaches
Using Neural Network
•
•
Clustering
Assignment 2 discussion
7.
8. CRISP-DM
9.
•
•
Time Series Mining
Mining Data Streams
•
•
Multi-Relational Data Mining
Data Mining for Fraud Detection
•
•
Introduction to Recommender System
Collaborative filtering
•
•
•
•
Data Mining Applications in real life
Research problems
Practicing in Kaggle
Tools and libraries
10.
11.
12.
13. Review and way forward