DM864: Advanced Data Mining

Comment

Entry requirements

None

Academic preconditions

Students taking the course are expected to:

Have basic knowledge of probability and mathematics;
Be able to program;
Be familiar with basics of unsupervised data mining (e.g. from DM555, DM566, DM583, DM843, DM868, DM870, or DS804).

Course introduction

The aim of the course is to enable the student to understand and work with advanced unsupervised data mining methods such as ensemble methods for clustering and outlier detection or methods dedicated to high-dimensional data (e.g., subspace clustering), which is important in regard to handle complex, difficult, and high-dimensional data in various applications.

The course builds on the knowledge acquired in the courses DM555, DM566, DM583, DM843, DM868, DM870, or DS804, and gives an academic basis for working in applied projects or writing a Master’s thesis in topics involving the unsupervised analysis of complex, difficult, and high-dimensional data.

In relation to the competence profile of the degree it is the explicit focus of the course to:

Give the competence to independently describe, analyse, and solve advanced problems in unsupervised data mining using the acquired models and methods.
Give the competence to analyse advantages and drawbacks of different methods for advanced unsupervised data mining.
Give skills to apply the acquired models and methods adequately.
Give knowledge and understanding of a selection of specialized models and methods for unsupervised data mining using ensemble techniques or adaptations to high-dimensional data, including some from the research frontier of the field.

Expected learning outcome

For at opnå kursets formål er det læringsmålet for kurset, at den studerende demonstrerer evnen til at:

beskrive de data mining opgaver som præsenteres i kurset;
beskrive de algoritmer og metoder som bliver præsenteret i kurset;
beskrive de emner der bliver præsenteret i kurset i et præcist matematisk sprog;
forklare de enkelte trin i de matematiske udledninger der præsenteres i kurset;
anvende metoderne på andre problemstillinger end dem der bliver præsenteret i kurset;
vurdere og reflektere over valg af design af data mining metoder for høj dimensional data og ensemble metoder.

Content

The following main topics are contained in the course:

general principles and methods for ensemble learning;
special challenges and approaches for ensemble clustering and ensemble outlier detection;
selected methods for ensemble clustering and ensemble outlier detection;
special challenges for data mining in high-dimensional data;
general approaches for unsupervised learning in high-dimensional data
selected methods for subspace clustering;
selected methods for high-dimensional outlier detection.

Literature

See itslearning for syllabus lists and additional literature references.

Examination regulations

Prerequisites for participating in the exam a)

Timing

Autumn

Tests

Oral presentation

EKA

N340084112

Assessment

Second examiner: None

Grading

Pass/Fail

Identification

Full name and SDU username

Language

Normally, the same as teaching language

Examination aids

To be announced during the course.

ECTS value

Additional information

Presentation of one or more scientific articles in class

The prerequisite examination is a prerequisite for participation in exam element a).

Exam element a)

Timing

Efterår

Prerequisites

Type	Prerequisite name	Prerequisite course
Examination part	Prerequisites for participating in the exam a)	N340084101, DM864: Advanced Data Mining

Tests

Report

EKA

N340084102

Assessment

Second examiner: None

Grading

Pass/Fail

Identification

Full name and SDU username

Language

Normally, the same as teaching language

Examination aids

A closer description of the exam rules will be posted in itslearning.

ECTS value

Additional information

The report should take up the topic of the oral presentation (an assigned paper) and compare it with some other presented papers (or papers discussed in the lectures).

Indicative number of lessons

30 hours per semester

Teaching Method

The teaching method is based on three phase model.

Intro phase: 22 hours
Skills training phase: 8 hours, hereof tutorials: 8 hours

Activities during the study phase:

Reading from textbooks and papers.
Solving homework.
Applying acquired knowledge in practical projects.

In the intro phase, concepts, theories, and models are introduced and put into perspective. In the training phase, students train their skills through exercises and dig deeper into the subject matter. In the study phase, students gain academic, personal, and social experiences that consolidate and further develop their scientific proficiency. Focus is on immersion, understanding, and development of collaborative skills.

Teacher responsible

Name	E-mail	Department
Arthur Zimek	zimek@imada.sdu.dk	Data Science

Timetable

Odense

Show full time table

Administrative Unit

Institut for Matematik og Datalogi (datalogi)

Team at Educational Law & Registration

NAT

Offered in

Odense

Recommended course of study

Profile	Education	Semester	Offer period

Transition rules

Transitional arrangements describe how a course replaces another course when changes are made to the course of study.

If a transitional arrangement has been made for a course, it will be stated in the list.

See transitional arrangements for all courses at the Faculty of Science.