96586 - Big Data

Learning outcomes

The laboratory allows students to learn the theoretical rudiments of modern statistical methods, with particular attention to methods for analyzing large data aggregates (big data) and statistical forecasting methods, in order to acquire the skills required to solve real-world problems and decision-making processes, also through practical examples and the use of specific software.

Course contents

This course is part of the University's experimental teaching project.


The focus of this lab is NOT on numbers or statistics, but on people. The EU AI Act represents the framework within which we will operate.


The approach will be predominantly humanistic. How does BIG DATA enable decision-making processes?


We will study the three main types of algorithmic learning used in machine learning:


supervised, unsupervised, and reinforcement.


Each of these allows us to answer these three questions:


What impact do they have on predictions? (supervised learning)


How do they generate detailed clusterings? (unsupervised learning)


Finally, how do they create alternative scenarios, following an IF... THEN... criterion? (reinforcement learning)


The lab therefore aims to raise awareness of the impact that BIG DATA has and will have on the real world.

Readings/Bibliography

This is a lab, so attendance is strongly recommended, as reading suggestions will be provided during the class, as the material is so new that the bibliography is constantly evolving.


However, it is essential to thoroughly read these texts, which serve as preparatory reading for the course:


Augmented Marketing. A Guide to New Martech Scenarios, by Vincenzo Cosenza, Apogeo


Dostoevsky's Artificial Intelligence. Reflections on the Future, Knowledge, and Human Responsibility. By Luca Mari, Il Sole 24 Ore


In the Beginning Was ChatGPT. Artificial Intelligence for Text, Images, Video, and What's to Come. By Mafe de Baggis, Alberto Puliafito. Apogeo


Machina Sapiens. The Algorithm That Stole the Secret of Knowledge. By Nello Cristianini, Il Mulino

Teaching methods

The course participates in the University's teaching experimentation project.


Lectures, group work

Assessment methods

The lab includes a final project work written by small groups.


The topic will be freely chosen. Each group will study the impact of BIG DATA on a specific topic and hypothesize which algorithms to use in the chosen field.


For those NOT attending: on the dates indicated as exam sessions, they will be required to prepare an individual project, taking into account the instructions in the textbook. In this project, no longer than 4 pages, they will apply the three types of algorithms to possible case studies. They will submit the project on the exam session day.

Teaching tools

Supporting slides will be provided, as well as research papers.

Office hours

See the website of Riccardo Pirazzoli