Objectives and outcomes
Students are introduced to many possibilities offered by big data analytics. They are able to identify
those that can be applied, developed and improved in a real environment, either by programming
specific solutions, using algorithm libraries or combining different tools. Knowing how to obtain big
data for analytics, how to extract, transform and store them in various forms, how to perform advanced
statistical analyses and analyses in the domain of artificial intelligence, students are able to
conceptualise and conduct both ad hoc analytical research on big data and projects for the development
of analytical applications.
Lectures
Through examples, students encounter the following concepts: data sampling, crawling, scraping,
application of statistics and machine learning in big data analytics, incomplete data, dirty data, outliers,
causality, correct and incorrect interpretation of results, ranking issues, weighting parameters, large text
analytics, analysis of social network graphs, classification of profiles on social networks, the
recommendation of content, and prediction of dropouts. Students are instructed how to cope with the
multitude of technological, methodological and domain alternatives to big data analytics.
Practical classes
Practical classes follow the content of the lectures and apply it in the open platforms Knime, Gephi and
Hadoop, as well as the programming languages Python and R. Students are trained to, using the tools
and techniques they are familiar with, independently perform advanced analytical big data processing.