The course has a strong mathematical and practical component. It is recommended to have passed the following courses:

- mathematical analysis

- calculus

- object-oriented programming

- data structures and algorithms

- statistical methods applied to engineering

- operations research







Related topics:

- computation

- statistics and operative research

- data mining

- artificial intelligence

- machine learning

By the end of the course the student will be able to:

Deal with statistical techniques for risk analysis and quality control.

Describe business intelligence fundamentals and techniques.

Apply decision support systems for decision making to particular tasks related to knowledge discovery, business intelligence and risk analysis.

Enumerate applications (e-commerce, decision support system frameworks, tools, assessment)

Decision-maker based model:

1. Algebra of preferences to model the preferences of a rational consistent decision-maker. Utility. Attitude to risk.

2. Decision tree building following a decision-maker's preferences. Optimal alternative finding in a decision tree. Examples in clinical decision.

3. Sensitivity analysis with one or multiple parameters.



Data-based model:

4. Introduction to supervised classification. Instances, attributes, class. Assessment of a prediction model (schemes and metrics).

5. Basic inference algorithms: k-NN (neighbor weighing), zero rules, one rule, decision treesbased on different impurity measures (predictive error, entropy, information gain, etc.), Naive Bayes. Model assessment. Supervised and unsupervised discretization. Attribute selection

6. Applications: Text mining; Business Intelligence; Clinical decision. International challenges: e.g. kaggle.

The course is on-site.



Lectures (denoted by "M" that stands for "Magistral" in Spanish): theoretical framework is given as well as exercises to exemplify the topics that shall be developed through practical exercises. Pro-active attitude and critical thinking are encouraged.



Labs with computer (denoted by "GO" that stands for "Grupo de Ordenador"): implementaion of systems making use of techniques studied through the aforementioned M methology. Autonomous work is encouraged.

• Continuous Assessment System
• Final Assessment System
• Tools and qualification percentages:
  • Written test to be taken (%): 50
  • Realization of Practical Work (exercises, cases or problems) (%): 50

Assessment parts and weighting: over 10.0 pts

40% (~ 4.0 pts): Labs and works carried out throughout the course

60% (~ 6.0 pts): Exam



Two requirements must be satisfied:

1. Achieve, at least, 40% on both parts i.e. minimum 1.6 points at labs and 2.4 points at the exam. 2. Summing up both parts together, achieve, at least, 5.0 points out of 10.0.

In order to evaluate the labs: in the ordinary call continuous assessment is carried out. In the remaining calls (either extraordinary call or calls taken in advance) a lab-exam is taken in replacement of the continuous assessment.



The student can decline to sit the exam, simply by not sitting the exam.

Assessment parts and weighting: over 10.0 pts

40% (~ 4.0 pts): Labs and works carried out throughout the course

60% (~ 6.0 pts): Exam



Two requirements must be satisfied:

1. Achieve, at least, 40% on both parts i.e. minimum 1.6 points at labs and 2.4 points at the exam. 2. Summing up both parts together, achieve, at least, 5.0 points out of 10.0.



In order to evaluate the labs: in the ordinary call continuous assessment is carried out. In the remaining calls (either extraordinary call or calls taken in advance) a lab-exam is taken in replacement of the continuous assessment.

eGela

Basic bibliography

- S. Ríos, C. Bielza, A. Mateos. Fundamentos de los sistemas de ayuda a la decisión. Ra-Ma, 2002.

- Ian Witten, Eibe Frank, Mark. Hall Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann, 2011 (4th Ed. 2017)

- E. Alpaydin. Introduction to Machine Learning. MIT Press, 2009 ó 2012

- E. Turban, R. Sharda, D. Delen. Decision Support and Business Intelligence Systems. Pearson, 2011

In-depth bibliography

- Tom Mitchell. Machine Learning. McGraw Hill, 1997.
- Richard O. Duda, Peter E. Hart, David G. Stork; Pattern Classification; Ed. Wiley-Interscience; 2 ed ISBN-13: 978- 0471056690
- C.M. Bishop; Pattern Recognition and Machine Learning. Springer. (2006).
- Alex Berson and Stephen J. Smith. Data Warehousing, Data Mining & OLAP. McGraw-Hill, 2001
- S. Holtzman. Intelligent decision systems. Addison Wesley, 1989.
- Business intelligence: Técnicas de análisis para la toma de decisiones. Elizabeth Vitt, Michael Luckevich, Stacia Misner. McGraw-Hill 2003.
- R. Clemen, T. Reilly. Making Hard Decisions. South Western, 2004

Journals

Decission Support Systems
Elsevier

Web addresses

http://dssresources.com
http://www.kdnuggets.com