This project brought together over 40 experts from national and international statistical organisations around the world to identify and tackle the main challenges of using Big Data sources for official statistics.
The project ran from January to December 2015, and focused on the following topics:
Task teams explored the potential of several Big Data sources to produce official statistics. This activity involved accessing data from the following sources, processing them and assessing their feasibilty as sources for official statistics. The results are reported in the following links:
- Wikipedia page views
- Trade data from the UN ComTrade Database
- Social media data from Twitter
- Data scraped from enterprise websites
The project team developed a sustainable model for the continuation of the "Sandbox" environment as a resource for the official statistics community, including identifying new use cases beyond Big Data.
- Options paper from the Sprint Session on the Future of the Sandbox (Cork, June 2015)
- Sandbox prospectus
- Sandbox brochure
3. Training and outreach
Various events took place during the project. Key presentations are linked below:
- Presentations from the UNECE Workshop on Big Data, (Brussels, March 2015)
- Sandbox presentation from the International Conference on Big Data for Official Statistics (Abu Dhabi, October 2015)
- Final project presentation, from the Workshop on Modernising Official Statistics (The Hague, November 2015)