|
Lecturer(s)
|
-
Gašpařík Adam, doc. RNDr. Ph.D.
-
Trnka David, Prof. Dr. Ing.
|
|
Course content
|
The course is intended for doctoral studies. Use of information and knowledge in decision-making processes. Processes of data mining in databases, CRISP-DM methodology. Sources of data mining: databases, statistical methods and machine learning. Machine learning methods: decision trees, decision rules, association rules, neural networks, genetic algorithms, and Bayesian learning methods. Use of statistical tools and machine learning tools in Statistica SW and Mathematica SW. Evaluation methods of designed models. Methods of data preparation. Overview of systems for data mining in databases. Principles of Decision Support Systems (DSS). Tools for creating Decision Support Systems. Predictive markets, their principles and applications in DSS.
|
|
Learning activities and teaching methods
|
- unspecified
- 80 hours per semester
- Presentation preparation (report in a foreign language) (10-15)
- 20 hours per semester
- Team project (50/number of students)
- 25 hours per semester
- Attendance on a field trip (number of real hours - maximum 8h/day)
- 11 hours per semester
- Individual project (40)
- 60 hours per semester
- Contact hours
- 24 hours per semester
- Preparation for comprehensive test (10-40)
- 40 hours per semester
|
| prerequisite |
|---|
| Knowledge |
|---|
| Build basic SQL statements to obtain the required data. |
| Apply knowledge acquired in courses KEM / STA, KEM / SZD and KEM / ADM. |
| Apply in practice the theory of statistical testing of hypotheses. |
| Analyze the dependence of two variables, apply the theory of regression functions of one explanatory variable. |
| Perform exploratory data analysis and verify their quality. |
| Work with covariance and correlation matrices. |
| Work with matrices, know their properties and apply matrix operations, find eigenvalues and eigenvectors. |
| Skills |
|---|
| Work with the selected database system to obtain the required data. |
| Work with an extended list of statistical functions in MS Excel. |
| Work with basic functions of SW Statistica (data loading, data modification, basic statistics, graphs). |
| Work with basic functions of SW Mathematica (basics of working with a laptop, inserting functions, working with hints, graphic functions). |
| Competences |
|---|
| create thesis in demanded structure use statistical methods on master level search articles in English and Czech |
| learning outcomes |
|---|
| Knowledge |
|---|
| Get an overview of selected data processing methods. |
| Understand the principles of selected methods, know the assumptions of their use. |
| Understand the outputs and know the procedures of subsequent interpretation. |
| Understand the principles of data mining and understand the criteria for selecting appropriate methods. |
| Skills |
|---|
| Choose the right methods with regard to the analysis of the problem. |
| Analyze and verify data quality. |
| Use practically selected methods in selected SW (Statistica, Mathematica, MS Excel). |
| Test models and compare them, interpret results based on outputs, apply results in their own decisions. |
| Apply results in your own decision making. |
| Competences |
|---|
| use advanced statistical and data mining methods apply suitable DSS software on practical problems |
| teaching methods |
|---|
| Knowledge |
|---|
| Lecture supplemented with a discussion |
| Seminar |
| E-learning |
| Self-study of literature |
| One-to-One tutorial |
| Group discussion |
| Individual study |
| Skills |
|---|
| Seminar |
| Interactive lecture |
| One-to-One tutorial |
| Group discussion |
| Competences |
|---|
| One-to-One tutorial |
| Seminar |
| Discussion |
| Students' portfolio |
| Interactive lecture |
| assessment methods |
|---|
| Knowledge |
|---|
| Oral exam |
| Project |
| Individual presentation at a seminar |
| Skills |
|---|
| Skills demonstration during practicum |
| Project |
| Seminar work |
| Individual presentation at a seminar |
| Competences |
|---|
| Seminar work |
| Skills demonstration during practicum |
| Project |
| Individual presentation at a seminar |
|
Recommended literature
|
-
Berka, Petr. Dobývání znalostí z databází. Vyd. 1. Praha : Academia, 2003. ISBN 80-200-1062-9.
-
Fotr, Jiří; Hájek, Jiří; Vrbová, Lucie. Počítačová podpora manažerského rozhodování. Vydání první. 2016. ISBN 978-80-245-2135-0.
-
Gangur, Mikuláš. Prediktivní trhy : principy, struktura a využití prediktivních trhů : pobídkové a motivační systémy prediktivních trhů : problematika implementace prediktivního trhu. Vydání první. 2015. ISBN 978-80-7478-847-5.
-
Hebák, Petr. Statistické myšlení a nástroje analýzy dat. Vyd. 1. Praha : Informatorium, 2013. ISBN 978-80-7333-105-4.
-
Hendl, Jan. Přehled statistických metod : analýza a metaanalýza dat. 2015. ISBN 978-80-262-0981-2.
-
Jensen, Finn V. Bayesian networks and decision graphs. New York : Springer, 2001. ISBN 0-387-95259-4.
-
Mitchell, Tom Michael. Machine learning. Boston : McGraw-Hill, 1997. ISBN 0-07-042807-7.
-
Rokach, Lior; Maimon, Oded. Data mining with decision trees : theory and applications. Hackensack : World Scientific, 2008. ISBN 978-981-277-171-1.
-
Rud, Olivia Parr. Data mining : praktický průvodce dolováním dat pro efektivní prodej, cílený marketing a podporu zákazníků (CRM). Vyd. 1. Praha : Computer Press, 2001. ISBN 80-7226-577-6.
-
Turban, Efraim; Aronson, Jay E.; Liang, Ting-Peng. Decision support systems and intelligent systems. 7th ed. Upper Saddle River : Pearson/Prentice Hall, 2005. ISBN 0-13-046106-7.
-
Vaughan Williams, Leighton. Prediction markets : theory and applications. New York : Routledge, 2011. ISBN 978-0-415-57286-6.
|