Marko Bohanec:
Systems and Techniques of Decision Support
Programmes:
Scheduled Lectures
Introductory lecture: 16.11.2010, 17:15-18:00
After the lecture, the work will be carried out individually and through consultations with the professor.
Practical Assignment Presentations and Examinations
- 15.6.2011 15:15, IPS Lecture Room
- 14.9.2011 15:15, IPS Lecture Room
Requirements and procedure
- Each student is required to make their Practical Assignment and write a report
(see the instructions below).
- The report must be sent by e-mail to
marko.bohanec@ijs.si
no later than the last Friday, 12:00 a.m., before the
presentation/examination event. Sending reports for earlier
previews is encouraged.
- A final printed version of the report must be handed to Marko Bohanec
at the presentation/examination event.
- Examinations: Each student should give a 10-15 minutes oral presentation
of their work (preferrably accompanied by PowerPoint slides).
- Discussion and oral examination will take place immediately after each student's
presentation.
Topics
Selected Reading
- Bohanec, M.:
Odločanje in modeli [Chapters 1-17].
DMFA - založništvo, 2006.
[O knjigi...]
- Interdisciplinarily
on Decision Making. Special Issue of Interdisciplinary Description of Complex
Systems 7(2), 2009.
- Jereb, E., Bohanec, M., Rajkovič, V.:
DEXi: Računalniški program za večparametrsko odločanje,
Moderna organizacija, Kranj, 2003.
- Bohanec, M.:
DEXi:
Program for Multi-Attribute Decision Making, User's Manual,
Version 3.00.
IJS Report DP-9989, Jožef Stefan Institute, Ljubljana, 2008.
- Bohanec, M., Messéan, A., Angevin, F., Žnidaršič, M.:
SMAC Advisor: A decision-support tool on coexistence of
genetically-modified and conventional maize.
Proc. Information Society IS 2006, Ljubljana, pp. 9-12, 2006.
- Žnidaršič, M., Bohanec, M., Kok, E.J., Prins, T.W.:
Qualitative risk assessment for adventitious presence of
unauthorized genetically modified organisms.
Proceedings of ISIT 2009, 1st International Conference on
Information Society and Information Technologies,
Novo mesto: Faculty of information studies.
12.-13.10.2009, Dolenjske Toplice, 7 p.,
2009.
- Žnidaršič, M., Bohanec, M., Lavrač, N., Cestnik, B.:
Project self-evaluation methodology: The Healthreats project case study.
Proc. Information Society IS 2009, Ljubljana, 85-88, 2009.
Web Pages
A Typical Practical Assignment
Goals:
- to understand two multi-attribute modelling methods (preferrably
a quantitative and qualitative one), and
- to be able to solve a medium-size real-life decision problem using
these two methods and corresponding software tools.
Method:
- Define your own decision-making problem.
- Create a multi-attribute model containing about 10-20 basic
attributes.
- Define about 4-6 alternatives (possibly real-life ones)
- Implement the model in:
- DEXi, and
- Quantitative modeling software of your choice (Web-HIPRE,
WinPre, spreadsheet, MATLAB, ...)
- Evaluate and analyse the alternatives.
- Write a report ... and submit it to your professor.
A completed practical assignment is required
to enter the final oral examination, and will account for 50% of the
final evaluation mark.
The report should consist of:
- Title page: Project title and Author info
- Main Part:
- Introduction:
- Description of the decision problem
- Aims and goals of your decision
- Description of attributes and their structure
- Description of alternatives
- Utilisation of the model:
- Evaluation of alternatives
- Analysis: Sensitivity and/or what-if analysis
- Conclusion:
- Which alternative to choose and why (its good and bad points)
- Brief comparison with other alternatives
- Appendices:
- Printout of your DEXi model
- Printout (or some other kind of documentation) of the quantitative model
Other Practical Assignments
Other types of practical assignments, related to decision making and
decision support, are possible in agreement with the professor. Some
examples: implementation of a decision-support method, comparison of
different methods, study of decision analysis software, implementation
of a decision-support solution, supplementing data mining with decision
support methods, etc. For complex decision problems, a development of
only one model may be sufficient.
Comments and suggestions to: marko.bohanec@ijs.si.
Last update: 20.4.2011