Personalized Multicriteria Decision Support Systems

You are here

Credits
4.5
Types
Elective
Requirements
This subject has not requirements, but it has got previous capacities
Department
URV;CS
Web
moodle URV
Mail
The student will be introduced to the research area of Multicriteria Decision Aid (MCDA).
The course covers three main issues:
(1) Preference structures for representing the interests of the decision maker. Special attention will be paid to the use of non-numerical information, such as linguistic variables, fuzzy sets or ontologies.
(2) Exploitation techniques of the user information to solve the decision problem. The two main approaches to MCDA will be studied: Multiattribute Utility Theory and Outranking Relations. At the end of the course, the student will have to know the theory, properties, advantages and drawbacks of those methods.
(3) Use of MCDA techniques in combination with other fields (f.i. Geographical Information Systems, Recommender Systems).
Free software will be used to practise.

Teachers

Person in charge

  • Aida Valls ( )

Weekly hours

Theory
1.8
Problems
0
Laboratory
0.9
Guided learning
0
Autonomous learning
4.5

Competences

Generic Technical Competences

Generic

  • CG3 - Capacity for modeling, calculation, simulation, development and implementation in technology and company engineering centers, particularly in research, development and innovation in all areas related to Artificial Intelligence.

Technical Competences of each Specialization

Academic

  • CEA12 - Capability to understand the advanced techniques of Knowledge Engineering, Machine Learning and Decision Support Systems, and to know how to design, implement and apply these techniques in the development of intelligent applications, services or systems.

Professional

  • CEP3 - Capacity for applying Artificial Intelligence techniques in technological and industrial environments to improve quality and productivity.

Transversal Competences

Information literacy

  • CT4 - Capacity for managing the acquisition, the structuring, analysis and visualization of data and information in the field of specialisation, and for critically assessing the results of this management.

Analisis y sintesis

  • CT7 - Capability to analyze and solve complex technical problems.

Objectives

  1. Recognize the main components of a decision making problem and decide the most appropriate modelization method.
    Related competences: CEA12, CG3, CEP3,
  2. Build a preference model according to the heterogeneous data types.
    Related competences: CEA12, CT7,
  3. Make an appropriate selection and use of aggregation operators.
    Related competences: CEA12, CEP3,
  4. Study and apply methods based on the Multi-Attribute Utility Theory.
    Related competences: CEA12, CEP3, CT4, CT7,
  5. Study and apply methods based on Outranking models for MCDA.
    Related competences: CEA12, CEP3, CT4, CT7,
  6. Identify the relations between MCDA (Multi-criteria Decision Aiding) and AI (Artificial Intelligence)
    Related competences: CEA12, CEP3,

Contents

  1. 1 Introduction
    "Multicriteria Decision Aiding" is a research field that is growing in importance recently.
    The use of AI techniques in this field is quite new and opens many interesting research lines.
    The first topic introduces the basic concepts and notation.

    1.1 The decision making problem. Formalization.
    1.2 MCDA applications
  2. 2 Preference representation models for user profiles
    To build personalised decision support systems we need to know and store the preferences of the users in an appropriate model. In this chapter, we study different representation models that take into account several data formats.

    2.1 Data types
    2.2 Family of criteria
    2.3 User profile construction and update
  3. 3 Multi-Attribute Utility Theory
    The course addresses two main approaches. The first is based on merging the utility of different criteria into a single overall score. Many fusion methods for aggregation will be presented and compared.

    3.1 Introduction
    3.2 Steps: aggregation and exploitation.
    3.3 Aggregation operators. Properties.
  4. 4 Models based on outranking relations
    The second approximation is more qualitative than quantitative. It is based on building a decision model with preference relations among a set of options.

    4.1 Introduction
    4.2 Outranking relations
    4.3 ELECTRE
  5. 5 MCDA and AI
    Use of MCDA in combination with other intelligent techniques can be applied in many different fields. Each course we study different lines according to the interests of the students. For example, MCDA in intelligent recommender systems, or in geographic information systems, or in web searchers, or electronic commerce, among others.

Activities

Activity Evaluation act


Exam

Final exam with questions and exercices
Objectives: 5 1 2 3 4
Week: 15 (Outside class hours)
Type: final exam
Theory
0h
Problems
0h
Laboratory
0h
Guided learning
2h
Autonomous learning
0h

Research report with an oral presentation

The student will make a survey on some topic, in group.The report is delivered to the teacher. An oral presentation will be done at class.
Objectives: 5 1 4 6
Week: 11
Type: assigment
Theory
0h
Problems
0h
Laboratory
0h
Guided learning
2h
Autonomous learning
20h

Solving practical exercices with software tools

The student will use a free software to solve some exercises. Some of them will be reported in a short document delivered to the teacher.
Objectives: 5 1 2 3 4 6
Week: 15
Type: lab exam
Theory
0h
Problems
0h
Laboratory
1h
Guided learning
0h
Autonomous learning
9h

Lectures

The lecturer explains the theoretical conceps of the subject with examples. Some complementary materials will be given to the students.
Objectives: 1 2 6
Contents:
Theory
27h
Problems
0h
Laboratory
0h
Guided learning
0h
Autonomous learning
26h

Practical exercises at the computer lab

The student will use a free software to solve some exercises. Some of them will be reported in a short document delivered to the teacher.
Objectives: 5 2 3 4
Contents:
Theory
0h
Problems
0h
Laboratory
12h
Guided learning
0h
Autonomous learning
12h

Teaching methodology

Oral exposition of the teacher
Oral presentations of the students
Practical exercices with software tools
Solving exercices in class

Evaluation methodology

Student must solve practical exercices with software tools 30%
Student must prepare a research report and make an oral presentation 30%
There is a final exam with short questions and exercises 40%

Bibliography

Basic:

  • Multiple criteria decision analysis : state of the art surveys - Figueira, José; Greco, Salvatore; Ehrgott, Matthias, Springer, c2005. ISBN: 978-0-387-23067-2
    http://cataleg.upc.edu/record=b1269711~S1*cat
  • Modeling decisions : information fusion and aggregation operators - Torra i Reventós, Vicenç; Narukawa, Yasuo, Springer, cop, 2007. ISBN: 978-3-540-68789-4
    http://cataleg.upc.edu/record=b1308961~S1*cat
  • Multi-criteria Decision Analysis: Methods and Software - Alessio Ishizaka, Philippe Nemery, Wiley, 2013. ISBN: 978-1-119-97407-9
  • Multicriteria Decision Aid and Artificial Intelligence - Doumpos, Michel, Grigoroudis, Evangelos, Wiley, 2013. ISBN: 978-1-119-97639-4

Web links

Previous capacities

None