Data Science Topics

No precedence over other disciplines is set and no recommended knowledge base is specified.

The teaching methods (ME) to be used are balanced between traditional and active and are as follows:
ME1 – Content exposure by the teacher (compatible with learning objectives 1, 2, 3, 4, 5, 6)
ME2 – Test the content learned by students (compatible with learning objectives 1, 2, 3, 4, 5, 6)
ME3 – Problem Solving by Students (Compatible with Learning Objectives 1, 2, 5, 6, 7)
ME4 – Interaction and sharing of ideas by students (compatible with learning objectives 1, 2, 5, 6, 7)
ME5 – Development of critical thinking by students (compatible with learning objectives 1, 2, 5, 6, 7)
ME6 – Research done by students (compatible with learning objectives 5, 7)
ME7 – Student-made creation (compatible with learning objectives 7)

The curricular unit is based on theoretical-practical classes. The teaching methods (ME) to be used are balanced between traditional and active. Classes include the presentation of concepts and methodologies and proceed with their discussion, as well as demonstrating the resolution of applied problems. In classes, concepts and methodologies are presented, content is discussed and problem solving is demonstrated. The content is taught and discussed in a classroom environment.

In addition to the traditional expository method, the methodology will include an investigation carried out by the students, where they will be challenged to investigate a certain topic and prepare and present an article on that topic, which may eventually be submitted to a scientific journal or to a conference. Teaching will also include project-based learning (PBL). As the name suggests, an active learning methodology that aims to associate learning with doing. This method is based on the construction of knowledge collectively, moving away from the conventional classroom model where the teacher teaches a subject and the students show how much they learned through a final assessment activity. The project proposed to be developed, preferably carried out in a group, aims to cover some of the phases of a data science project.

The main learning objectives (LO) defined are the following:

• LO1 – Know the central role of data in an organizations value creation strategy
• LO2 – Understand how data-driven thinking is structured and streamlined
• LO3 – Know possible applications of data science projects in various sectors of activity
• LO4 – Know the main concepts and techniques related to data science
• LO5 – Become aware of some of the main sources of data at national and international level
• LO6 – Understand the main aspects related to the phases of a data science project
• LO7 – Know how to apply in a practical project some of the main concepts and approaches learned

The main skills (S) that are intended to be developed are the following:

• S01 – Ability to recognize translating an organization’s objectives into the objectives of a data science project
• S02 – Competence in identifying, understanding and preparing the data necessary for a data science project
• S03 – Ability to plan a data science project, covering the main stages of that project
• S04 – Ability to search for and identify open data that responds to the needs of a data science project on a topic
• S05 – Ability to propose the most appropriate modeling technique for a given problem

1 Data, its transformation into value and data-driven thinking
2 Data science and applications across multiple domains
3 Those involved in a data science project
4 The main techniques of data science
5 National and international data sources
6 The data science lifecycle(s)
7 Natural language processing (NLP)
8 Analysis of practical cases
9 Tools used in data science
10 Main data science problems and challenges

Assessment may occur in two ways: by examination or continuous assessment, and will comprise six components: a final written exam (EFE), the writing of a scientific article (AC), the completion of a practical project (PP), the results of which will be presented in a session specifically scheduled for this purpose, which will take place during any of the regulatory examination periods, and also a continuous assessment by attendance (ACF), a continuous assessment of the scientific article (ACAC), and a continuous assessment of the practical project (ACPP).

The ACAC or ACPP components are based on the components of the scientific article (AC) or the Practical Project (PP), and the difference compared to the conventional assessment of these components is that the student has an opportunity for continuous assessment. Students may apply for an ACAC or ACPP, which will take place during class time and is subject to the timely submission of the article and project components and a minimum of 3/4 attendance in classes. Continuous assessment based on attendance is also subject to a minimum of 3/4 attendance in classes. The ACPP does not invalidate the student's right to be re-evaluated by exam in the project component. To do so, the student must submit and defend a significantly improved version of the project on the established dates for the respective periods.

Exam Evaluation:

• The exam evaluation includes 3 components: the Final Written Exam (EFE), the Scientific Article (AC), and a Practical Project (PP).
• Final grade = 40% x EFE + 20% x AC + 40% x PP

Continuous Assessment:

• The continuous assessment includes 3 components: the ACF, the Continuous Assessment of the Scientific Article (ACAC), and the Continuous Assessment of the Practical Project (ACPP).
• Final grade = 40% x ACF + 20% x ACPP + 40% x ACPP

The final grade for the course will be calculated as the weighted average of these components, rounded to the nearest integer. The final grade is calculated by rounding the result of the formula presented above to the nearest whole number. If there is an equal distance between the lower and upper integers, the rounding is done towards the higher integer. For example, if the final grade is 9.5 points, then it will round up to 10 points.

NAO