Decision Sciences
Objectives
At the end of this course the student will have acquired knowledge, skills and competences within the studied topics:
- Be able distinguish among decision under uncertainty, risk, mono-criterion and multicriteria. To know the main drawbacks of quantitative methods for decision support and to be able to make a critical analysis of the solutions.
- Understand the differences between the paradigms of mono and multi-objective optimization. To know and to apply techniques for the reach the solution of compromise.
- Comprehend concepts such as discrete event simulation, entity, state, pseudo-random number, replica, among others. To identify which technique should be use to simulate different and complex systems.
Comprehend the concepts of Data Mining and to be able to identify and apply algorithms to large data structures.
- Be able to select and use adequate software.
General characterization
Code
12972
Credits
9.0
Responsible teacher
Maria Isabel Azevedo Rodrigues Gomes
Hours
Weekly - 2
Total - 24
Teaching language
Inglês
Prerequisites
Available soon
Bibliography
Gomes, M. I., & Martins, N. C. (2022). Mathematical Models for Decision Making with Multiple Perspectives: An Introduction. CRC Press.
J.N.Clímaco, C.H. Antunes, M.J.G.Alves, Programação linear multiobjectivo, Universidade de Coimbra, 2003.
J.Figueira, S.Greco, M.Ehrgott, Multiple Criteria Decision Analysis. State of the Art Surveys, Springer, 2005.
P.Goodwin, G.Wright, Decision Analysis for Management Judgement, John Wiley & Sons, 2010.
R.E.Steuer, Multiple Criteria Optimizations: Theory, Computation, and Application, Krieger Pub Co, 1989.
T.Tanino, T.Tanaka, M.Inuiguchi, Multi-Objective Programming and Goal Programming, Springer, 2003.
Teaching method
Tutorial guidance oriented to the achievement of objectives.
Research work.
Evaluation method
Available soon
Subject matter
(The particular techniques taught may vary slightly from year to year)
- Single and multi-criteria decision making (decision under uncertainty and risk; decision trees; utility theory; multi-criteria decision methodologies: compensatory, non-compensatory and hierarchical).
- Multiobjective optimization (dominance and efficiency; addictive models; weighted vector models; admissible space reduction methods; interactive methods; goal programming).
- Simulation (discrete time vs. continuous time simulation; generating pseudo-random numbers; experiment design and output analysis).
- Data Mining (clustering, association rules, classification algorithms, outliers detection, prediction, result analysis).
Programs
Programs where the course is taught: