Page 397 - Contributed Paper Session (CPS) - Volume 4
P. 397
CPS2449 Louisa Nolan et al.
• Optimus - a tool to turn free text into hierarchical datasets (3) to
understand the movement of goods in the UK.
These projects use a range of administrative data, geospatial data, data
from the Internet of Things, and text, and tools and techniques including
machine learning, natural language processing and distributed computing to
give fresh insights into the UK economy and the business behaviours which
drive it. In Section 2, we briefly summarise our approach, and in Section 3,
present an overview of the results. In Section 4, we discuss these results, and
conclude with a summary of our findings.
2. Methodology
2.1 Faster indicators of UK economic activity
The faster indicator project set out to fast indicators of the UK economy
using novel data sources based on administrative data and data from the
Internet of Things. It has three objectives:
• to identify close-to-real-time data which represent useful economic
concepts
• to create early warning indicators of potentially large economic
changes
• to provide new insights into economic activity, particularly around UK
ports
It is important to note that we are not attempting to forecast or predict
gross domestic product (GDP) or other headline economic statistics here, and
the indicators should not be used in this way. Rather, by exploring big, closer-
to-real-time datasets of activity likely to have an impact on the economy, we
provide an early picture of a range of activities that supplement official
economic statistics and may aid economic and monetary policymakers and
analysts in interpreting the economic situation in a timely way.
From UK VAT data, we have created, with industry breakdowns where
possible:
• several monthly and quarterly diffusion indices from turnover and
expenditure VAT returns
• novel indicators tracking changes in VAT reporting (counts of
repayments, re-inputs and replacements)
• a proxy for firm births, based on counts of new VAT reporters.
We created shipping indicators from automatic identification system (AIS)
data, which tracks ship location every few seconds whilst the ship is moving
and every couple of minutes whilst it is in port, using data from the UK
Maritime and Coastguard Agency, and, via the UN Global Platform, from
ORBCOMM. We have used the data to construct monthly indicators of the
time spent in port by ships, and the frequency of visits to ports, for the 10
386 | I S I W S C 2 0 1 9