Code
MUFE MIS 3402
Niveau
L3
Discipline
Systèmes d’information
Langue
Anglais/English
Crédits ECTS
3
Heures programmées
18
Charge totale étudiant
60
Coordonnateur(s)
Département
- Data analytics, Économie et Finances
Equipe pédagogique
Introduction au module
This course introduces students to the fundamental concepts of data science using Python, developing the analytical skills needed to extract meaningful insights from real business data. Through a project-based format, students work with actual datasets to cover the key stages of the data lifecycle — from collection, cleaning, and exploration to statistical analysis and causal reasoning — building the foundations for more advanced data and AI courses in subsequent years.
This course requires a personal computer (tablets are not recommended), active participation throughout, and a willingness to engage with both code and statistical concepts from the very first session. Students who arrive prepared and engaged will leave with the analytical foundations and data intuition needed to contribute to evidence-based decision-making in their professional lives.
Bloc de compétences
- 6. Concevoir et/ou piloter des solutions de gestion innovantes en veillant à garantir une création de valeur soutenable pour toutes les parties prenantes
Compétences du bloc
- 6.2 - Optimiser l'usage d'outils adaptés aux différents domaines de gestion, et définir et interpréter les KPI pertinents, afin de mesurer et garantir une création de valeur durable et soutenable pour toutes les parties prenantes.
Objectifs d'apprentissage du cours
At the end of this PGE1(L3) course, each student will be able to:
1- Identify and distinguish between economic data types (cross-sectional, time-series, panel) and select appropriate descriptive statistics (mean, median, variance, standard deviation, quartiles) to characterize a dataset, producing outputs that a non-technical reader can interpret.
2- Use Python and Pandas in a Colab environment to load, clean, merge, and manipulate a structured dataset — including handling missing values, renaming variables, filtering rows, and creating new variables — with or without AI assistance, verifying outputs critically before use.
3- Select and produce appropriate visualizations (histograms, bar charts, box plots, scatter plots) for a given analytical question, and interpret distributional properties (normality, skewness, outliers) in a business dataset.
4- Apply probability concepts and sampling theory to construct and interpret confidence intervals, distinguishing between population parameters and sample estimates and explaining what uncertainty means in a specific business context.
5- Conduct and interpret a hypothesis test (t-test) on a real dataset — specifying the null and alternative hypotheses, interpreting the p-value, and distinguishing between statistical significance and practical significance for a business decision.
6- Distinguish between correlation and causation, identify confounders and selection bias in a given business scenario, and evaluate whether a difference-in-differences design or A/B test would support a causal claim.
7- Estimate and interpret a multiple linear regression model — including coefficients, R-squared, adjusted R-squared, and dummy variables — verify key model assumptions, and translate regression output into a business recommendation.
8- Use AI tools to support statistical analysis — including generating and debugging code, interpreting outputs, and stress-testing conclusions — while documenting the boundary between AI assistance and original team reasoning in the final report.
Contenu : structure du module et agenda
Block A — Foundations
Session 1: Course intro, Python/Colab setup, variables, data types, lists, basic operations, economic data types. Dataset bank introduced — groups formed, datasets assigned. HW1 assigned
Session 2: Descriptive statistics, Pandas basics. Guided practice on group dataset. HW1 due. HW2 assigned. MCQ 1 due
Session 3: Data cleaning and manipulation. Guided practice on group dataset. HW2 due. HW3 assigned.
Block B — Data Analysis
Session 4 : Visualization — histograms, bar charts, box plots, scatter plots, choosing the right chart for the right question. Guided practice on group dataset.
Session 5 : Probability basics, normal and binomial distributions, population vs. sample, Central Limit Theorem intuition, confidence intervals. Guided practice on group dataset. HW3 due. HW4 assigned. MCQ 2 due.
Block C — Inference, Causality, Regression
Session 6 : Hypothesis testing — null/alternative hypothesis, p-value, t-test, practical vs. statistical significance. Correlation. Guided practice on group dataset. HW4 due.
Session 7: Correlation vs. causation — confounders, selection bias. Causal inference introduction: DiD , A/B testing. Guided practice on group dataset.
Session 8: Simple and multiple linear regression — coefficients, R-squared, adjusted R-squared, dummy variables, model assumptions. Guided practice on group dataset. HW5 assigned
Block D — Wrap-up
Session 9: Final report due - including HW5. Group presentations. Individual exam.
Contribution à l'atteinte des ODD (Objets du Développement Durable)
This course contributes to ODD 4 by developing data literacy and critical analytical skills in students from non-technical backgrounds, providing an inclusive foundation in data science that is essential for navigating an increasingly data-driven professional and social environment. It contributes to ODD 8 by equipping students with the practical Python and statistical skills needed to contribute to data-driven organisations, supporting their employability and readiness for the evolving demands of the labour market. It contributes to ODD 10 by deliberately lowering the barriers to technical education — designing a course that requires no prior programming or statistics background, ensuring that access to data science skills is not limited to students from quantitative or engineering disciplines.
Nombre d'ODD abordés parmi les 17
3 ODD
Méthode pédagogique
This course is based on a learning-by-doing approach. The classes will include a theoretical component, which will cover the essential concepts, as well as a practical component where the theory will be applied through programming exercises.
Système de notation et modalités de rattrapage
Continuous assessment (MCQ 2×10% + group project report and presentation 40%): MCQs evaluate students' knowledge of content presented each day. The group project requires 4 partial submissions (on time submission for bonus), a report and a presentation. In the group project students will be applying course concepts to their case study. Individual contributions to the group project are tracked via shared Colab notebook history.
Final exam (40%, paper-based): Given a short business scenario and statistical output, students interpret regression results, evaluate whether a causal or correlational claim is justified, and explain the implications of a statistical test for the business decision at stake. The exam covers the core concepts from the course.
Rattrapage: Only the failed component(s) need to be retaken: a new MCQ, a new individual written exam on the same learning objectives, or a new project based on a different dataset with the same deliverable structure. All rattrapage work is followed by an individual oral exam.
Règlement du module
Professor-Student Communication
● The professor will contact the students through their school email address (IMT-BS/TSP) and the Moodle portal. No communication via personal email addresses will take place. It is the student responsibility to regularly check their IMT-BS/TSP mailbox.
● Students can communicate with the professor by emailing him/her to his institutional address. If necessary, it is possible to meet the professor in his office during office-hours or by appointment.
Students with accommodation needs
If a student has a disability that will prevent from completing the described work or require any kind of accommodation, he may inform the program director (with supporting documents) as soon as possible. Also, students are encouraged to discuss it with the professor.
Class behavior
● Out of courtesy for the professor and classmates, all mobile phones, electronic games or other devices that generate sound should be turned off during class.
● Students should avoid disruptive and disrespectful behavior such as: arriving late, leaving early, careless behavior (e.g. sleeping, reading a non-course material, using vulgar language, over-speaking, eating, drinking, etc.). A warning may be given on the first infraction of these rules. Repeated violators will be penalized and may face expulsion from the class and/or other disciplinary proceedings.
● The tolerated delay is 5 minutes. Attendance will be declared on Moodle during these 5 minutes via a QR code provided by the teacher at each course start.
● Student should arrive on time for exams and other assessments. No one will be allowed to enter the classroom once the first person has finished the exam and left the room. There is absolutely no exception to this rule. No student can continue to take an exam once the time is up. No student may leave the room during an examination unless he / she has finished and handed over all the documents.
● In the case of remote learning, the student must keep his camera on unless instructed otherwise by the professor.
Honor code
IMT-BS is committed to a policy of honesty in the academic community. Conduct that compromises this policy may result in academic and / or disciplinary sanctions. Students must refrain from cheating, lying, plagiarizing and stealing. This includes completing your own original work and giving credit to any other person whose ideas and printed materials (including those from the Internet) are paraphrased or quoted directly. Any student who violates or helps another student violate academic behavior standards will be penalized according to IMT-BS rules.
Références obligatoires et lectures suggérées
VanderPlas, J. (2023). Python Data Science Handbook (2nd ed.). O'Reilly.
Huntington-Klein, N. (2022). The Effect: An Introduction to Research Design and Causality. Chapman and Hall/CRC.
Cunningham, S. (2021). Causal Inference: The Mixtape. Yale University Press.
Mots-clés
Python, Jupyter Notebook, Data Science