In the first term, from September to the end of December, you will take four courses of 6 ec each:
The second term, which lasts from January to the end of June, you will start with the Internship Data-driven Consultancy. This consists of two parts. The first part is a consultancy project for a real client, this part is offered in January. For the second part, students need to participate a few times as a consultant in the Methodology Shop. The office hours are spread over the whole year, and students will be scheduled beforehand.
The rest of January and Semester 2 are dedicated to the internship and the thesis.
The course provides a general overview of the structure of a data science project, and a training on several practical skills that are necessary to carry out the different stages of such a project. This encompasses training on interview techniques, data wrangling with R, an introduction to SQL, statistical modelling, data visualisations, and principles about reporting results of a data science project.
This course offers an introduction to data analytics and machine learning for large unstructured data sets. You will master statistical learning methods, feature extraction from unstructured data (such as text file parsing, signal processing, and elementary image feature extraction), and data merging skills. Algorithms are covered at both the conceptual and computational level. The emphasis of the course is on practical applications in a range of (commercial) settings.
This course encompasses the construction of reliable and valid metrics, in particular the construction of psychological tests. The statistical techniques suitable for the evaluation of the reliability and validity of these tests and other types of measurement instruments (questionnaires, exams, online learning applications, etc.) are treated both in theory and practice. Both classical test theory and modern test theory, including factor analysis and item response theory, will be considered.
During the Internship Data-Driven Consultancy, you will carry out a real-life data science project under supervision, and you will serve as an advisor to fellow students regarding questions about research methodology and statistics.
During the main external internship (15 EC), you will work for a company or (public) institution and gain experience in applying your acquired knowledge and skills to real-life challenges. You are encouraged to find and organise the external internship independently, but we also host a yearly internship event in collaboration with Amsterdam Data Science.
You will write a Master's thesis which fits the knowledge objectives of the Master's track.
In the first period you will take one elective. Network Analysis or Deep Learning in Python.
The purpose of the thesis is to answer a scientific question relating to behavioural data science. It is possible to combine the external internship and the thesis into one project (36 EC).