12:00 - 13:00
Invited Paper Session
Room: Hegelsaal I
Chair:
Aurel Schubert
Organiser/s:
Per Nymand-Andersen
This session will address the challenges of working with structured and unstructured micro-level data often referred to as big data. What are the challenges in the current digital and technical transformation and how can the statistician benefit from these developments. This session will present results from using big data for supplementing the existing available statistics. The challenges of using big data tools, techniques in detecting outliers, modelling for providing new insights, ethical considerations, sharing of data among official institutions, skills and techniques of data scientists
The use of granular data to produce high quality statistics: challenges and perspectives
Antonio Matas Mir
European Central Bank, Frankfurt

Abstract

The collection of granular data has been one of the major shifts in the compilation of central bank statistics in the last twenty years. The increase in computing power and storage capacity, and the corresponding increasing digitalisation of the economy, has transformed the statistical landscape and the “business as usual” of financial statistics. Granular data allow flexibility and thus to meet better changing user needs; they reveal the heterogeneity in the economy, the concentration of risks, and the interconnectedness of the entities; and they map better the intricacies and flows of a globalised world. Finally, and perhaps crucially, they allow collecting data once to serve a variety of purposes.

Nevertheless, granular data face substantial challenges and necessitate a paradigm shift if they are to achieve their multiple goals. The change in the scale of the statistical units analysed – from the sector level information, to the credit institution and down to the transaction ­– requires the identification of entities and objects in a standardised manner. Granular data also impose consistency and homogeneity on the data at source (through the use of generic and detailed reporting formats), as well as authoritative reference databases. The globalised nature of financial entities requires increased international cooperation between collecting authorities and close work with the reporting entities. Last but not least, they also need the transformation of the internal organisation to collect, process, store, and integrate the data inside the collecting institutions.

These challenges are being addressed at the ECB in different ways. We provide an overview of selected endeavours in the field of securities issuance, holding statistics and financial accounts, showing the path from reference databases, through the collection of granular data and the intermediate outputs, to aggregate statistics with a full granular foundation.


Reference:
Th-IPS02-02
Session:
The need for granular data and the impact of new private data sources
Presenter/s:
Antonio Matas Mir
Presentation type:
Oral presentation
Room:
Hegelsaal I
Chair:
Aurel Schubert
Date:
Thursday, 18 October 2018
Time:
12:00 - 13:00
Session times:
12:00 - 13:00