Visual Analytics for Big Data

FaculteitFaculty of Science

NiveauMaster

Studiejaar2026-2027

Beschrijving

Course goals

After completing this course, students will be able to:

classify typical user tasks for exploratory and confirmatory data visualization in the context of the domain situation and select appropriate visualization techniques to address these tasks.
represent large, complex, time-dependent, and multidimensional data optimally to enable visual exploration.
design and use interactive pipelines to visually explore real-world data using state-of-the-art visualization techniques.
communicate findings, as well as system design decisions, to stakeholders.

Assessment

During the course, students will work in groups to complete the end-to-end project. The project will consist of three subgoals and one grand goal. The three subgoals are to be completed by groupwork. The grand goal is to be completed individually by each student.

Students are assessed as follows:

group project report (40% of the final grade)
group presentation (20%)
individual project report (40%)

To pass the course, the student needs to have a passing grade for both the group and individual grades.
The group grade is calculated by combining the grades from the group project report and the group presentation.

To qualify for a repair of the final result the mark needs to be at least a 4, or “AANV”.

Prerequisites

Basic knowledge of statistics; general data structures and algorithms; programming experience (any mainstream general-purpose language) are required.

Enrolment in this course is only available by using the pre-enrolment form that will be forwarded to all ADSM students in the first week of November.

Content

Are you eager to harness the power of Visual Analytics to tackle the challenges posed by Big Data in modern applications?

This course will equip you with the skills to represent, analyze, and interact with large datasets visually. By combining theoretical foundations with hands-on practice, you will explore how Visual Analytics can transform raw data into meaningful information to uncover insights and answer critical questions, thus aiding decision-making and sensemaking. We do this by offering a grounding in the following themes.

1. Data representation: You will learn to define and distinguish Visual Analytics from other types of data visualization. You will gain proficiency in representing different types of Big Data, such as time series, multidimensional data, and other unstructured data, so that the data is directly amenable to visual exploration.

2. Visual analysis techniques: You will gain familiarity with several practical Visual Analytics techniques and understand the rules of visual encoding and design — such as visual variables, perception, inverse mapping, linked views, interaction, color usage, annotations, managing visual clutter,

high information density, and visual minimalism. You will learn to apply these techniques using a set of modern information visualization methods that go beyond simple static charts – parallel coordinates, node-link diagrams, projections, and treemaps.

3. Problem solving: A unique feature of this course is the integration of data from the annual IEEE Visual Analytics Science and Technology (VAST) Challenge, which offers realistic tasks and up-to-date datasets to be explored with Visual Analytics tools and workflows. By working with VAST Challenge data with fellow students, you will engage with real-world problems that require advanced Visual Analytics solutions to generate new insights and make a significant societal impact.

In this course, you will:

form and refine hypotheses before analyzing data to avoid common pitfalls such as HARKing and Type I Errors and improve analysis quality.
thoroughly examine the problem scenario, including reviewing background materials and understanding the provided questions.
learn to map problems to data by systematically examining data schemas, summary statistics, and data samples, thus cultivating critical thinking and problem-solving skills.
engage in iterative and collaborative design that promotes teamwork and communication by following a structured, step-by-step process for efficient and effective Big Data analysis.
develop and use meaningful visualizations that support hypothesis testing and data-driven storytelling using e.g. Tableau or D3
-learn to communicate findings and hypotheses clearly and effectively, which is crucial for reporting back to various stakeholders.

Course form

(guest) lectures
practical work (design, implement, fine-tune visual analytics methods to complete an end-to-end project)
individual and group project assignments

The lectures teach the theoretical part of the course’s three themes. The work sessions teach practical skills in actually coding/using the theory taught during the lectures. Using this input, students are asked to construct, use (and reflect on the obtained results) an end-to-end Visual Analytics system that addresses a real-world problem on complex data (see theme 3). Students are provided with feedback on their progress during the work sessions.

Literature
The course has no mandatory book. Rather, the lecturer will provide detailed syllabi, documentation, slides, example demos (and datasets) which will fully cover the taught material.

Reviews0 reviews

Nog geen reviews voor dit vak. Wees de eerste!

Heb jij dit vak gevolgd?

Deel je ervaring met toekomstige studenten. Inloggen met je Universiteit Utrecht mailadres duurt één minuut.

Schrijf een review