Data Analytics

Recommended prior knowledge corresponds to the fundamental Statistics content included in the Mathematics curricula for the different levels of compulsory education in Portugal (http://www.dge.mec.pt/), namely:

• PK1. Basic knowledge of descriptive statistics.
• PK2. Ability to interpret statistical tables, graphs and indicators.
• PK3. Basic computer skills and proficiency in the use of common software applications.

• TM1. Theoretical-Practical Classes: In accordance with the curriculum, classes are theoretical-practical in nature and are planned and designed to promote students’ active engagement throughout different stages or the entirety of each class.
• TM2. Interactive Lectures: The theoretical component, including the introduction of concepts, methods, and fundamental results, will be delivered through lectures complemented by strategies that promote active student participation (interactive lectures). These strategies include questions posed by both the instructor and the students, either orally or through digital platforms, as well as debates and small-group discussions on the topics addressed.
• TM3. Guided Problem Solving and Practical Activities: The practical component is designed to fully develop the intended competencies through guided demonstrations of procedures and/or problem-solving activities under the instructor’s supervision. Independent work and small-group collaboration will be encouraged. A strong integration between theory and practice will be emphasized, with particular focus, whenever possible, on the visualization and analysis of real-world situations.
• TM4. Independent Learning: The development of the competencies defined for this course requires active and regular participation in class, together with the independent completion of the activities proposed before, during, and after the face-to-face sessions.
• TM5. Learning Resources: All supporting materials will be made available through the InforEstudante|Nonio platform. Additional digital platforms may also be used whenever appropriate to support teaching activities and promote interaction with students.

Statistical data analysis plays a fundamental role in a wide range of business contexts by supporting the description and diagnosis of phenomena of interest, as well as data-driven decision making. In this course, students develop competencies in descriptive and diagnostic data analysis while acquiring fundamental knowledge of time series analysis.

Learning outcomes:

• LO1. Portray, statistically, the dataset under analysis.
• LO2. Extract relevant information about a phenomenon, by conducting descriptive or diagnostic analysis of the associated dataset.
• LO3. Adapt the descriptive techniques to be applied in the case of time series.

Competencies to be developed:

• SC1. Situation/Problem Identification: Recognize situations that may benefit from the application of descriptive, diagnostic, or time series analysis techniques.
• SC2. Technique Selection: Identify, among a set of basic statistical techniques, those suitable for processing a certain dataset.
• SC3. Data Management: Build a data dictionary composed of fundamental metadata for the analysis to be carried out.
• SC4. Data Quality: Carry out a summary assessment of the quality of the data based on the defined quality dimensions.
• SC5. Statistical Analysis: Perform univariate and bivariate descriptive analyses.
• SC6. Data Preparation: Transform and/or engineer new features that allow solving some more technical issues of the analysis and/or bringing new insights.
• SC7. Anomaly Detection: Detect anomalies in a dataset.
• SC8. Time Series Analysis: Execute descriptive analysis for time series data.
• SC9. Software Utilization: Use software to support generate the results.

• P1. Background to data analysis
  1.1. Goals of descriptive analysis and diagnostic analysis
  1.2. Particularities of temporal data.
• P2. Descriptive analysis
  2.1. Univariate analysis
  2.2. Bivariate analysis
• P3. Diagnostic analysis
  3.1. Transformation and design of new features
  3.2. Anomaly detection: missing values and outliers – first approach
• P4. Introduction to time series
  4.1. Components
  4.2. Trend lines
  4.3. Decomposition

In accordance with the Academic Regulations for First-Cycle Studies of the Polytechnic University of Coimbra (IPC), assessment in this course unit may be completed under one of the following assessment schemes.

A) Continuous assessment

This assessment scheme comprises three compulsory assessment components: one practical group assignment and two written tests.

MA1. Practical group assignment (30%)

• Weight: 6 points.
• The assignment is completed in groups of 2 to 4 students.
• The assignment is organised into successive stages. The lecturer will define progress meetings for the submission of the different stages and for monitoring the development of the work. The corresponding schedule will be published at the beginning of the semester through InforEstudante|Nonio. Attendance at these progress meetings is compulsory for all group members, although each student may miss, at most, one meeting.
• Failure to submit any compulsory stage results in that stage not being assessed.

MA2. Written test 1 (35%)

• Weight: 7 points.
• Minimum required mark: 2.5 points.

MA3. Written test 2 (35%)

• Weight: 7 points.
• Minimum required mark: 2.5 points.

Final grade formula:

FG = MA1 + MA2 + MA3

The final grade is calculated provided that the student obtains a minimum mark of 2.5 points in both assessment components MA2 and MA3. Failure to meet this requirement results in failure under this assessment scheme.

Additional provisions for continuous assessment:

• Eligibility for the continuous assessment scheme requires a minimum attendance rate of 50% of the classes.
• Written tests MA2 and MA3 are closed-book examinations and cover all course content taught up to the class immediately preceding the respective test.
• If a student is absent from a written test, regardless of the reason, no alternative test will be scheduled, and a mark of 0 (zero) will be awarded.

B) Examination assessment

This assessment scheme comprises two compulsory assessment components: one written examination and one individual practical assignment, both completed on the official examination date.

MA4. Written examination (70%)

• Weight: 14 points.
• Closed-book examination.

MA5. Individual practical assignment (30%)

• Weight: 6 points.
• Intended for students who did not complete the practical group assignment (MA1) under the continuous assessment scheme.

Final grade formula:

FG = MA4 + MA5

The final grade corresponds to the sum of the marks obtained in the practical assignment and the written examination.

General assessment regulations:

• Passing the course unit: Under either assessment scheme, students pass the course unit if they obtain a final grade, rounded to the nearest whole number, of 10 points or higher.
• Use of computers during assessments: All assessment components are conducted on a computer using the software employed during classes and, where applicable, one or more institutional platforms requiring institutional authentication. Students are responsible for ensuring that they know the relevant passwords to access these platforms.
• Validity of the practical assignment: The mark obtained in practical group assignment MA1 under the continuous assessment scheme remains valid for the regular, supplementary and special examination periods.
• Practical assignment during the regular, supplementary and special examination periods: Students who have completed Practical Assignment MA1 under the continuous assessment scheme are required to take only the written examination (MA4). Students who have not completed Practical Assignment MA1 under the continuous assessment scheme must complete the examination-based assessment, consisting of the written examination (MA4) and the individual practical assignment (MA5).
• Guidelines on the use of Artificial Intelligence: The use of Generative Artificial Intelligence tools is not permitted during assessment components MA2, MA3 and MA4. For practical assignments MA1 and MA5, the use of such tools is permitted to support the development of the work, provided that their use is responsible, critical and properly acknowledged. Whenever requested by the lecturer, students must provide the prompts used and the content generated by the Artificial Intelligence tools.
• Academic misconduct: Where there are well-founded suspicions of academic misconduct identified during the marking process, the student will be required to attend an oral examination to verify the knowledge and competences demonstrated. This examination will be conducted by a panel consisting of the course lecturer and two additional lecturers from the same academic field. If the student is unable to demonstrate the knowledge and competences evidenced in the written assessment, the assessment will be declared void.
• Working student status: Assessment of students holding Working Student Status shall be governed by the provisions of the Academic Regulations for First-Cycle Studies of the Polytechnic University of Coimbra.
• Grade improvement: For the purpose of grade improvement, students may choose one of the following options:

a) Students who completed practical group assignment MA1 under the continuous assessment scheme may retake only the written examination (MA4), with the MA1 mark remaining unchanged.

b) Students who were assessed under the examination assessment scheme must complete a new examination assessment in full, consisting of the written examination (MA4) and the individual practical assignment (MA5).

NAO