CRM & Information Mining I
level of course unit
second cycle, Master
Learning outcomes of course unit
Instruction in the basic topics of data warehouse systems and information mining (data/web/social Content) will be given in this course. The material will be structured as follows:
Data warehouse systems: factual knowledge and content competence; architecture and structure of data warehouses; difference between transactional data and data analysis; basic knowledge of multidimensional and practical data modeling (star schema, snowflake schema, etc., plus selection of the correct model); basics of the ETL process, OLAP operations and graphic modeling with various data models, e.g. M ER storage of multidimensional data: ROLAP (relational) versus MOLAP (multidimensional variant); index structures for data warehouses: multidimensional index structures and their optimizing possibilities: star joins and partitioning, optimization of OLAP operations.
Information mining: basic principles of information mining (statistics, machine learning and database systems); data structures for data mining and KDD; clustering: hierarchical cluster, k-means, DBSCAN; basic techniques (association rules (a priori algorithm, etc.), classification (naive Bayes, etc.), regression, etc.); support vector machines; decision trees; machine learning in practice; time series; application of the techniques and methods in text, data, the web and social web environment; applications for data mining concepts (e.g. in price setting for budget flights, in calculating insurance premiums, in credit decisions and in marketing, etc.).
prerequisites and co-requisites
The students will acquire detailed knowledge of the basic techniques, tasks and areas of application of a data warehouse system.
The students will also acquire detailed skills in methods for obtaining specialized know-how, and will be aware of their multidimensional modeling possibilities.
In this connection they will also be conversant with the various established means of storage (ROLAP, MOLAP), and will be able to apply these specifically and increase system efficiency by using optimizing techniques.
The second focal point of this course is acquiring in-depth knowledge of available algorithms and methods of information mining. The students will be able to use these specifically for data and web mining.
recommended or required reading
- Andreas Bauer, Holger Günzel: Data-Warehouse-Systeme : Architektur, Entwicklung, Anwendung, Heidelberg : dpunkt-Verl., 2001;
- Ian H. Witten, Eibe Frank: Data Mining: praktische Werkzeuge und Techniken für das maschinelle Lernen, Hanser, 2001.
- Wolfgang Lehner: Datenbanktechnologie für Data-Warehouse-Systeme : Konzepte und Methoden, Heidelberg, dpunkt, 2003.
assessment methods and criteria
language of instruction
number of ECTS credits allocated
planned learning activities and teaching methods
group work, individual work, presentation, duscussion
semester/trimester when the course unit is delivered
name of lecturer(s)
Dr. Michael Kohlegger
year of study
recommended optional program components
course unit code
type of course unit
compulsory (integrated lecture)
mode of delivery