Co-chairs: John Hinde and Costas Bekas
Description: This WG will develop Task 5. Open source software will be developed following standard rules in order to make the computational methods widely accessible for researchers in related topics and practitioners. The algorithms developed by WG C will be implemented in R, which is currently the leader free environment for data analysis, and other open-source languages. The capacity of these environments to cope with large datasets is still limited. Issues that relate to their ability to extract, transform, load and process big data needs to be addressed. Research in this direction will be developed, e.g., by incorporating fast matrix approximation techniques based on stochastic techniques. The elaboration of visualization tools to facilitate the inspection of large non- standard data sets will also be considered.