Decision Theory

The main objective of the course is a detailed presentation of the theoretical and practical framework of the concept and content of decision theory and the importance they have for the modern business. Also, the methodological decision documentation, schemes and algorithms appropriate to address real problems and situations on a business level by exploiting the technology offered by Information Technology.

Objectives

The main objective of the course is a detailed presentation of the theoretical and practical framework of the concept and content of decision theory and the importance they have for modern enterprises. Also, the methodological decision documentation, schemes and algorithms appropriate to address real problems and situations on a business level by exploiting the technology offered by Information Technology and the Internet. After completing the course, students should learn: The basic of Bayes decision theory, the two categories classification problem, decision regions and error probabilities. Also, the normal probability density and the discriminant functions for this density. How to use the parameter calculation techniques and guided learning as data analysis tools for making financial and administrative decisions. How to use algorithms and decision theory techniques and to integrate them in the data analysis process for making financial and administrative decisions. How to investigate systematically the effects of alternative methodologies, algorithms, techniques and strategies of decision theory in making financial and administrative decisions. How to evaluate and assess different algorithms/techniques of decision theory and use them as decision support tools in Information Systems.

Prerequisites

There aren't.

Syllabus

The main objective of the course is a detailed presentation of the theoretical and practical framework of the concept and content of decision theory and the importance they have for the new digital era internet business. Also, the methodological decision documentation, schemes and algorithms appropriate to address real problems and situations on a business level by exploiting the technology offered by computers and the Internet. The topics and lectures of the course are: 1st Lecture: Introduction to Decision Theory. Pattern Recognition Systems / Decision Making. 2nd Lecture: Bayesian Decision Theory. Classifiers, discriminant function and Decision surfaces. Error probabilities and intervals. 3rd Lecture: Bayesian Decision Theory. Presentation of examples and solution of exercises. 4th Lecture: Problem Solving with Search Algorithms. 5th Lecture: Informed Search and Exploration. 6th Lecture: Local Search Algorithms and Optimization Problems, Search Algorithms (Exercises) 7th Lecture: Constraint Satisfaction Problems. 8th Lecture: Adversarial Search. 9th Lecture: Uncertainty, Statistical Learning, maximum likelihood 10th Lecture: Simple Decisions Making 11th Lecture: Presenting selected examples and solving selected exercises. 12th Lecture: Solving selected exercises from past exams.