Skip to main content
Data Science for the Sustainable Development Goals
Course Description

The United Nations and international organizations are increasingly using network and data science methods to support their development and humanitarian activities. This introductory course aims at providing students with insights on how data-related methods are used to tackle and monitor the Sustainable Development Goals (SDGs). It gives an overview of current applications, and a critical understanding of the challenges and limitations of such approaches.

The core of the learning activities will be through the instructor’s lectures, one or two invited seminars by experts working at international organizations, and a number of hands-on sessions with python notebooks, where the students will have the opportunity to put into practice the methods introduced during the course through the exploration of a specific open dataset and research question (e.g. estimating poverty from social media data).

The course is planned to cover the following topics:

  • Challenges and limitation of digital data (e.g. privacy, access and biases)
  • Challenges in using data- and model-driven insights for decision and policy making (e.g. models’ explainability, operationalization, etc.)
  • Specific applications (subject to changes based on students’ interests): socioeconomic inequalities (e.g. poverty and hunger), migration (e.g. migration flows and migrant integration within cities), gender inequalities, environmental sustainability and climate change.
Learning Outcomes
  • Developing familiarity with the Sustainable Development Goals and related data science applications;
  • Developing a critical understanding of the challenges and limitations of the use of digital data and related methods for humanitarian and development purposes;
  • Gaining in-depth knowledge and skills about a specific related topic/application.
Assessment

The final grading will be based on three elements:

  • Individual participation in class (10%)
  • Oral presentation about a case study related to one of the covered topics (40%)
  • Final assignment (50%), which can be either of the following, depending on what skills the student is more interested in developing: (1) systematic literature review on a topic of interest; (2) individual project in which the student will design a simple research question and produce an original data analysis and modeling on an open dataset.
Prerequisites

Notions of statistics and basic programming skills are desirable.

Course Level
Master’s
Doctoral
Academic Year
2023-2024
Term
Winter
US Credits
2
ECTS Credits
4
Course Code
DNDS6032