About this course
Data on food and consumer behavior are complex in nature due to an interplay between product characteristics (e.g., nutritional properties, food quality attributes, labeling, packaging), consumer characteristics (e.g., dietary restrictions, knowledge, lifestyle), and varying contexts and situations (up to and including weather conditions). To be able to gain a better understanding of these complex phenomena an interdisciplinary data science perspective is required. In this course, a deeper knowledge will be gained regarding the application of data science methods and techniques in the domain of food and consumer science. Students will work on cases from the food and consumer science domain and thereby apply their data science skills and learn more about such applications in the domain of food and consumer behavior. Research questions and queries need to be defined to the food and consumer behavior. Data sets related to food composition, recipes, food pictures, purchase data, search behavior data, store layout, and promotion data, etc. Data will be cleaned, processed, explored, visualized, and used to develop prediction models. The results will be presented in a poster presentation. Special attention is given to communication to the domain experts, by means of a workshop on visualization and storytelling with data. In addition, the internal and external validity of the data that is analyzed will be discussed in detail with the domain experts. Next to the case study, students will read and discuss selected scientific papers. In this discussion, special attention will go to the validity and interpretation of food and consumer data, and to the additional value of applying data science techniques to the traditional methods of data analyses that are currently used in this domain.
After successful completion of this course students are expected to be able to:
- choose and appraise relevant research questions in the domain of food and consumer science;
- appraise the potential of data science techniques to address those questions;
- select and collect relevant data sets;
- apply data wrangling/cleaning and visualization techniques to the data;
- apply data science algorithms and prediction models to the data;
- document and present the results by means of visualization techniques and storytelling, but also make the data FAIR;
- discuss the internal and external validity of different types of data and results;
- critically discuss a scientific paper from the food and consumer data domain.
INF34306 Data Science Concepts, HNH37006 Data Science for Health: Principles and MAT32806 Statistics for Data Scientists
Basic programming R and/or Python, data wrangling, basics of making visualizations, basic statistical skills, clustering methods, prediction models