Applications for the class of 2020-2022 are still open for self-financed students. Apply here

Deadline : June 15th, 2020 (midnight, Paris time).  Applications for scholarships are closed. 


Covid-19 updates: during the Covid-19 pandemic, the SERP+ master is taking measures to ensure that learning can continue with new teaching and assessment methods.

Master SERP+ Programme

Data Science Basics


Content

  1. The Cross-industry standard process for data mining (CRISP-DM) model.
  2. Data Collection and Business Understanding.
  3. Modelling
    1. Exploratory Data Analysis;
    2. Predictive Analytics.
  4. Evaluation methodologies.

Aims

The syllabus contents defined for this course unit are intended to provide the student with knowledge of the essential steps to a Data Science project. The goal is that the student will be able to define the problem, collect data, apply and evaluate some of the main modeling techniques and interpret the obtained results.

Recommended Books

  1. L. Torgo. Data Mining with R, learning with case studies, second edition, 2017. Chapman and Hall/CRC . ISBN: 9781482234893
  2. J. Han , M. Kamber and J. Pei. Data Mining - Concepts and Techniques (3rd edition), 2011. ISBN: 9780123814791.

Teaching Staff

Rita Ribeiro (responsible)

Hours

21 h (lectures + theoretical-practical classes)

Grading System

During classes topics will be exposed with the help of practical examples.

Evaluation will be carried out in a distribution form together with a final exam.

This course uses distributed evaluation formed by two (2) theoretical tests during the semester (or alternatively a final exam), and one (1) practical assignment at the end of the semester.

The final grade will be calculated as the weighted average of the practical and theoretical grades using the following formula:

NF = 0.60 * NTh + 0.40 * NPra

where, NTh is the average of the grades in the two tests or the grade in the final exam, and NPra is the grade of the practical assignment.