1. Início
  2. NOVA Information Management School
  3. Pós-Graduação em Análise e Gestão de Informação
  4. Métodos Descritivos de Data Mining

Métodos Descritivos de Data Mining

Objetivos

Data Mining uses interdisciplinary techniques, such as statistics, data visualization, database systems, and machine learning to identify original, useful, and understandable patterns in data.
This course will familiarize students with Data Mining applications and Data Mining projects' lifecycle. Students will learn techniques for understanding and preparing data before building descriptive models, such as clustering or association rules (e.g., market basket analysis).

Caracterização geral

Código

200165

Créditos

7.5

Professor responsável

Roberto André Pereira Henriques

Horas

Semanais - A disponibilizar brevemente

Totais - A disponibilizar brevemente

Idioma de ensino

Português. No caso de existirem alunos de Erasmus, as aulas serão leccionadas em Inglês

Pré-requisitos

Familiarity with the main theme of the course is not required. But it is highly recommended that the students have knowledge of Inferential Statistics as well as good skills as a computer user.

Students without previous training or experience with Python should complete the two following Datacamp online courses before the third week of this course (first practical class):  Introduction to Python and Intermediate Python. Students who wish could also complete, optionally, the course Data manipulation with pandas. The instructor will provide information on how to have free access to the Datacamp platform.

Bibliografia

Método de ensino

The course is based on theoretical and practical classes. Several teaching strategies are applied, including slides presentation, step-by-step instructions on approaching practical examples, and questions and answers. The practical component is oriented towards exploring the tools introduced to students (Microsoft Excel and Python) and the development of the project.

Applications used: Microsoft Excel, Python, Jupyter notebook, Microsoft visual studio code.

Método de avaliação

Due to the application-based design of the course, evaluation is continuous and applies to both the theory and practical components. There is no ¿one only exam¿ with a single weight of 100%.

All evaluation grades are on a scale of 0-20.

  • Python Quiz:
    • Individual - with materials consultation
    • The minimum grade is 8.0
    • 10% weight
  • Group project:
    • The minimum grade is 8.0
    • 40% weight
  • Exam:
    • Individual - with materials consultation
    • The minimum grade is 8.0
    • 1st season or 2nd season: 50% weight

All submissions should be made via Moodle. Submissions after the deadline will be rejected.

Conteúdo

LU1. Introduction to Data Mining
LU2. Methodological aspects (KDD, SEMMA, CRISP-DM)
LU3. Data understanding
LU4. Data visualization
LU5. Data preparation
LU6. Association rules and the Apriori algorithm
LU7. Data similarity and dissimilarity measures
LU8. RFM model
LU9. Clustering

Cursos

Cursos onde a unidade curricular é leccionada: