Data Mining I

Code:

2MDA01

Acronym:

ECD I

Keywords
Classification	Keyword
OFICIAL	Information Technology

Instance: 2020/2021 - 1S

Active?	Yes
Web Page:	http://moodle.up.pt/course/view.php?id=480
Course/CS Responsible:	Master in Modeling, Data Analysis and Decision Support Systems

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
MADSAD	38	Official Syllabus - after 2020-2021	1	-	6	42	162

Teaching language

English

Objectives

At the end of the semester students should have the knowledge of various Data Mining tasks, the main methods and algorithms for each task, be able to apply these methods to new specific data analysis problems and have the capacity to evaluate, apply a critical posture in relation to results.

Learning outcomes and competences

Knowledge of various Data Mining tasks, the main methods and algorithms for each task, be able to apply these methods to new specific data analysis problems and have the capacity to evaluate, apply a critical posture in relation to results.

Working method

Presencial

Program

- Machine learning, data mining. - From OTLP to OLAP. Multidimensional databases. - Knowledge: Representation. Generalization and specialization. - Data: Examples and instances of concepts. Attributes and values. Signal and noise. Multi-relational representations. Types of attributes. Data formats for data mining systems. Exploratory data analysis. - Distance-based methods. Algorithm k-NN and its properties. - Probabilistic methods. Bayesian classifiers. - Methods based on search. Decision trees and rules. Covering algorithm. - Evaluation of classification models. Costs. Overfitting. - Pre-processing: Feature selection, discretization, dealing with unknown values and outliers. - Advanced topics of classification. - Regression. Evaluation of regression models. - Frequent patterns, association rules. - Cluster analysis. - Methods for combination of models. Voting methods. Methods based on samples. Hierarchical combination of models. Data Mining tools. - Methodologies of data mining projects (CRISP-DM).

Mandatory literature

J. Gama, A. Carvalho, K. Faceli, A. Lorena, M. Oliveira; Extração de Conhecimento de Dados, Silabo, 2012. ISBN: 978-972-618-698-4
Jiawei Han; Data Mining: Concepts and Techniques, Moegan Kaufman, 2006
Tom M. Mitchell; Machine learning, McGraw Hill, 1997
an Witten, Eibe Frank; Data Mining: practical machine learning tools and Techniques with java implementations, Morgan Kaufmann, 2000
David Hand, Heikki Mannila; Padhraic Smyth;Principles of Data Mining, MIT Press, 2001

Teaching methods and learning activities

Theoretical and practical classes

Software

Weka -> http://www.cs.waikato.ac.nz/ml/weka/
R -> http://www.r-project.org/
Knime

keywords

Technological sciences > Technology > Information technology
Physical sciences > Computer science > Cybernetics > Artificial intelligence

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Designation	Weight (%)
Exame	50,00
Participação presencial	0,00
Trabalho escrito	50,00
Total:	100,00

Amount of time allocated to each course unit

Designation	Time (hours)
Elaboração de projeto	50,00
Frequência das aulas	42,00
Trabalho escrito	50,00
Apresentação/discussão de um trabalho científico	15,00
Estudo autónomo	5,00
Total:	162,00

Eligibility for exams

Weighted sum of home works and exam >= 9.5

0.5 * Exam + 0.5 (average of the works)

Calculation formula of final grade

Exam 50% Practical work 50% The mark of practical work is calculated as the mean of practical works carried out. The practical work not done has a mark of 0. The minimum mark of the exam is 6.5. The minimum mark of the practical work is 6.5