New Opportunities through Visual Analytics for Big Data

In many occasions, decision-makers have to analyze large amounts of data. Intelligent support systems try to aid analysts to reach effective decisions, while handling large amounts of data. In NOVA, we focus on the interpretability challenge, investigating which level of information abstraction is necessary for effective problem solving tasks.

In many occasions, decision-makers have to analyze large amounts of data. Intelligent support systems try to aid analysts to reach effective decisions, while handling large amounts of data. However, in complex cases, the users have difficulties reasoning about the system behavior, leading to mistrust and misuse of such systems. To mitigate the lack of intelligibility, explanations and representations of the inner workings and outcomes of the data-mining modules can be used. But, how do we present the inferences made by intelligent support systems and their inner workings to users? Is it actually beneficial to show inner workings and detailed information regarding the data mining modules? If so, to which costs?

In NOVA, we focus on the interpretability challenge, investigating which level of information abstraction is necessary for effective problem solving tasks. Empirical studies with experts from our partner companies, Combitech AB (network security and logistics) and Takara Bio Europe AB (gene regulatory systems) will be carried out.

Project leader

The project in short

Fully name of project:
New Opportunities through Visual Analytics for Big Data (NOVA)

Durance: 2 years

Financed by:
Knowledge Foundation

Collaborating partners/Partnership:
Combitech AB and Takara Bio Europe AB.

Researchers related to the current project

Jane Synnergren, PhD, Senior Lecturer in Bioinformatics

Per M. Gustavsson, PhD, Principal Research Scientist, Combitech

Catharina Ellerström, PhD, Director R&D at Takara Bio Europe AB