Data and text mining

Data mining is a research area that concerns methods, techniques and tools for analyzing large data sets in order to support decision making. Research in this area may be found under several headings, including machine learning, knowledge discovery, predictive analytics and intelligent data analysis.

A particular focus of our research is on predictive data mining using ensemble methods, i.e., techniques for generating sets of models that collectively form predictions by voting, and on methods for generating interpretable models, e.g., rule learning.

Text mining is a sub-field of data mining, which handles data in the form of natural language documents, e.g., news paper articles, web pages, scientific papers and electronic patient records. 

Our research here focuses on efficient and resource lean methods using language technology for very large text sets.

The main application area for our research is health care analytics, which aims for providing efficient and effective decision support for health care and pharmaceutical research.