Page 146 - Special Topic Session (STS) - Volume 4
P. 146
STS571 Ossi Nurmi et al.
The use of mobile phone data in
Tourism Statistics
Ossi Nurmi; Pasi Piela
Statistics Finland
Abstract
Survey response rates are declining at an alarming rate globally. Statisticians
have traditionally used imputing and recalibration of weights to deal with
nonresponse. In case survey response rates are well below 50 %, these
methods may often result in little more than guesswork. Alternative data
sources need to be used to improve the accuracy of statistical estimates. In
the context of outbound tourism, mobile positioning data can be considered
as such an alternative data source as it registers ‘traces’ of tourism trips. These
traces are CDRs (call detail records) and DDRs (data detail records) and they
are generated by the activities of mobile devices. Since 2016 Statistics Finland
has worked closely with Finnish national mobile network operators (MNOs) to
translate the CDRs and DDRs into tourism specific monthly aggregates such
as number and duration of trips by destination country. Statistics Finland has
learned that it helps to be very specific when approaching MNOs with data
needs. This paper provides a summary of the methodological process that the
Finnish MNOs have followed to compile tourism statistics. A similar process
may be used by National Statistics Institutes or other organizations who are
approaching their national MNOs with the intent of obtaining data. The paper
then presents the 2017 outbound tourism data from Finnish MNOs and
highlights the shortcomings of the Finnish national tourism survey in light of
mobile positioning data. Based on this analysis, the paper proposes a method
to enrich the tourism survey using mobile positioning data. One of the main
needs for outbound tourism data comes from the Balance of Payments (BoP)
statistics. The debit side of BoP requires quarterly data by destination country
and purpose of trip. More accurate data is needed to reliably estimate the
expenditure of resident tourists abroad. The paper proposes a method where
mobile positioning data is first used to estimate the number and duration of
outbound trips by country and month. The role of tourism survey data is then
to provide ratios such as purpose of trip, means of transport and average
expenditure. In this method the tourism survey is no longer needed for
estimating the absolute number of trips.
Keywords
Mobile Positioning; Tourism; Geospatial data
135 | I S I W S C 2 0 1 9