DATA MANAGEMENT

Digital data management is a key skill for challenging complexity. The quality of decisions and strategies involving individuals and organizations increasingly depends on the ability to extract, filter and assemble digital data from which to infer operational information to solve practical problems.
The objective of the module is to provide methodological, theoretical and application guidelines to learn how to effectively manage the phases of acquisition, storage, processing and representation of digital data, with a specific focus on the potential of Machine Learning and on the main functions of Data Analysis tools.
At the end of the course, students will be able to develop a digital data management project for solving a practical problem assigned by the teacher.

1. Knowledge and understanding:
- students will be able to describe the characteristics of digital data and the criteria for evaluating the quality of the data
- students will be able to describe the six stages of the digital data management process
- students will be able to describe the fundamental models for data processing
- students will be able to list some software applications for digital data management

2. Ability to apply knowledge and understanding:
- students will be able to use software applications for research and acquisition of digital data
- students will be able to use programs for archiving and indexing data
- students will be able to apply basic methods to process digital data
- students will be able to implement tools for data visualization and representation

3. Judgment skills:
- students will be able to contextualize the knowledge acquired, identifying the models, methods and software most suitable for the desired output

4. Communication skills:
- students will be able to effectively present the results of data analysis
- students will be able to interact with colleagues and the teacher, according to the objectives of the course

5. Learning skills:
- students will be able to use and integrate information from notes, handouts, slides and practical exercises
- students will be able to evaluate their level of preparation through practical and laboratory activities

The course is aimed at those who want to enhance their specific skills through elementary techniques for researching, organizing, interpreting and viewing digital data in the various disciplinary areas, in order to improve the quality of their forecasts and decisions. Therefore, beyond basic computer skills, no specific technical knowledge in coding or software for information processing is required, nor are mathematical skills higher than those of high schools, technical and professional institutes.

The course is structured into two parallel modules:

MODULE 1 – The New Digital Intelligence

Didactic Unit 1: Digital Intelligence and Data Management
- The effects of digitalization on reality
- The concept of “digital intelligence”
- The six dimensions: data acquisition, memory, computation, representation, activation, and adaptation

Didactic Unit 2: Building and Storing Digital Data
- Methods of acquisition and conversion of digital data
- The logical structure of a dataset
- Features and functions of digital memory

Didactic Unit 3: Systems and Models for Digital Data Processing
- From digital data to information
- Computation and system modeling techniques
- Machine Learning algorithms: classification, regression, clustering, and time series analysis

Didactic Unit 4: The Color of Digital Data
- Processes of data and information representation and communication
- Types of charts, diagrams, and infographics
- Multimedia principles of Data Visualization

Didactic Unit 5: Activation, Mechanical Decision-Makers, and Adaptation
- Dashboards supporting decision-making processes
- Turning data into decisions
- Monitoring the digital data management process

MODULE 2 – Digital Data Management Lab
- Phases of a Machine Learning project
- Introduction to the Orange Data Mining software
- Binary classification
- Natural Language Processing
- Multiclass classification
- Image processing
- Regression
- Time series analysis
- Clustering techniques
- LLMs and generative AI tools

[1] MODULE 1 - G.B. Ronsivalle, "La nuova intelligenza digitale. Come trasformare i dati in decisioni per progettare il futuro", Maggioli Editore, Collana Apogeo Education, 2022.
[2] MODULE 2 - G.B. Ronsivalle, I. Baccan, A. Bersan, "The Orange Box. Laboratorio di Machine Learning", Edizioni Wemole, 2024.

The final examination is divided into two steps:

Step 1 – Online Written Test
An online written exam assessing basic theoretical knowledge.
The test consists of a digital questionnaire including open-ended questions.

Step 2 – Group Project Work
A group project focused on the application of elementary techniques for digital data management.
Students are required to develop a workflow using Orange Data Mining and to present a short report describing the different phases of the project: data acquisition, storage, processing, and representation, aimed at solving a practical problem assigned by the instructor.

Challenge
Student groups may take part in a series of Data Science and Machine Learning challenges proposed by the instructor, designed to enhance their practical skills in digital data management.

written and oral

Step 1: Online Written Test (individual)
- Maximum score: 15 points
- Minimum passing score: 9 points

Step 2: Project Work (group)
- Maximum score: 15 points
- Minimum passing score: 9 points

Challenge (group)
- Additional bonus: 0 to 5 points

Final Grade = Step 1 Score + Step 2 Score + Challenge Bonus = x/30

The lectures alternate (a) theoretical presentation sessions supported by multimedia slides, (b) interaction activities on the topics of the course, (c) case studies, (d) individual and group exercises using Data Science platforms , (and) simulations. The course also includes the publication of videotutorials to present the characteristics and functions of data management software.

This subject deals with topics related to the macro-area "Human capital, health, education" and contributes to the achievement of one or more goals of U. N. Agenda for Sustainable Development