Introduction. Categories of decisions in modern firms. Architecture of a Decision Support System. Analysis of discrete options’ decision problems. Influence Diagrams - Decision Trees. Creation of models, solution, risk profiles and sensitivity analysis. Utility functions and their use for decision support. Role and value of perfect and imperfect information - Bayes theorem use. Multi-criteria decision making. Structure and capabilities of software tools for the analysis of discrete options’ decision problems. Analysis of decision problems with continuous range of options - Linear Programming - Creation of models, solution and sensitivity analysis. Structure and capabilities of software tools for the analysis of decision problems with continuous range of options. Basic concepts, structure and design of data warehouses – star, constellation and snowflake schemes. Techniques of data mining for extraction of knowledge from data in order to provide decision support. Structure and capabilities of datawarehousing and datamining software tools. The laboratory of this course includes familiarization with software tools for the analysis of both discrete options and continuous ranges of options decision problems, and also data warehousing and data mining tools.

The main learning outcomes of this course are:

• Understanding basic methods for the analysis of decision problems of firms and public organizations based on the creation of models and the solution of them.
• Understanding basic methods for supporting decision making in firms and public organizations based on the provision of appropriate forms of processed information to the decision-makers, and the extraction from the available data of knowledge useful for decision making.
•  Familiarization with software tools supporting the above tasks 1 and 2.
• Development of ability to model decision problems, and then to solve the models, understand the results, and use them for drawing conclusions and formulate proposals-recommendations for the decision makers.
• Development of ability to exploit the data of ‘traditional’ internal on-line transaction processing systems of firms and public organizations, and also other external sources, through appropriate processing, for providing support to various levels and types of decision makers.

Not required.

1. Loukis, E., ‘Decision Support Systems Strategy – University Lectures’(in Greek).

1. Turban, E., Aronson, J., Liang, T. P., ‘Decision Support Systems and Intelligent Systems, Prentice-Hall International, 2007.
2. Bertsimas, D., Freund, R. M., ‘Data, Models and Decisions’, Dynamic Ideas Publishing, 2004.
3. Clemen R. T., ‘Making Hard Decisions - An Introduction to Decision Analysis, Duxbury Press, 1996.
4. Laudon, K. C., Laudon, J. P., ‘Management Information Systems: Managing the Digital Firm’, Prentice Hall 2012.
5. Jarke, M., Lenzerini, M., Vassiliou, Y., Vassiliadis, P., ‘Fundamentals of Data Warehouses’, Springer-Verlag, 2003.
6. Siskos, J., ‘Linear Programming’, NewTech Publications, 1998.
7. Ypsilantis, P., ‘Operational Research – Applications in the Modern Enterprise’, Propompos Publications, 2008.
8. Mitchell, T. M., ‘Machine Learning, McGraw-Hill International Editions, 1997.
9. Nanopoulos, A., Manolopoulos, J., ‘Introduction to Data Mining and Data Warehousing’, NewTech Publications, 2010.
10. Doukidis, G., ‘Innovation, Strategy, Growth and Information Systems’, Andreas Sideris – Ioannis Sideris Publications, 2010 (in Greek).

Final examination and lab exercises (theoretical and programming).
The mark of the lab should be ≥ 5 for attendance in the final examinations. The mark of the team exercise should be ≥ 5 for attendance in the final examinations. The mark of final examination should be ≥ 5 for successful course completion. The final mark is computed as follows: 0.4 * (Mark of Lab) + 0.4 * (Mark of Examination) + 0.2 * (Mark of team Exercise) and should be ≥ 5.

For each examination/exercises subject clearly specified evaluation criteria are given. The students can see their exam paper after the final examination and inspect their faults. The overall distribution of marks is announced on eClass, so that students can evaluate their performance.

Face-to-face.