Forecasting London Museum Visitors Using Google Trends Data (Research Note)
1. ENTER 2018 Research Track Slide Number 1
Forecasting
London Museum Visitors
Using Google Trends Data
Ekaterina Volcheka, Haiyan Songa, Rob Lawa and Dimitrios Buhalisb
a The Hong Kong Polytechnic University/ School of Hotel and Tourism Management, Hong Kong
katerina.volchek@connect.polyu.hk, haiyan.song@polyu.edu.hk, rob.law@polyu.edu.hk
bBournemouth University/ Department of Tourism and Hospitality, UK
dbuhalis@bournemouth.ac.uk
2. ENTER 2018 Research Track Slide Number 2
Forecasting of Tourist Behaviour
(Song, Witt, & Li, 2008; Pan, Wu, & Song, 2012; Yang, Pan, & Song, 2014).
Historical
aggregated data
Real-time, high-
volume, and high-
frequency data
Data Statistics
Econometrics
•Artificial
intelligence
Methods
Proliferation of technologies, PCs, and the Internet
Availability of high-volumes of high-frequency
historical and real-time data on tourist behaviour
3. ENTER 2018 Research Track Slide Number 3
Forecasting of Tourist Behaviour
with Online Search Data
Kadir, Tahir, Yassin, & Zabidi, 2014;
Pan et al., 2012;
Yang et al., 2014
Etc.
Arrivals/
Destinations Demand
Artola et al., 2015;
Bangwayo-Skeete & Skeete, 2015;
Choi & Varian, 2012;
Li et al., 2017;
Önder, 2017;
Park et al., 2017;
Xiang & Pan, 2011;
Yang et al., 2015
Etc.
Hotel room demand
Attractions demand
Huang, Zhang, & Ding, 2017
4. ENTER 2018 Research Track Slide Number 4
Decision Making in Tourism
Awareness Interest Desire Action
INFORMATION SEARCH
5. ENTER 2018 Research Track Slide Number 5
Decision Making in Tourism
Before Trip During Trip After Trip
Arrivals/
Destination
Choice
Room demand /
Hotel Choice
Attractions Visits /
Attraction Choice
6. ENTER 2018 Research Track Slide Number 6
To investigate the opportunity
to forecast the number of museum
visitors based on tourist online search
behaviour
Research Aim
7. ENTER 2018 Research Track Slide Number 7
Methodology:
Applied data
• Most-visited London Museums (free entrance)
• Monthly data since January 2012 till September 2017:
• Total number of visits
• Google Trends index (worldwide) for selected keywords
Attraction Search Query Searched as Category
The British Museum British Museum Museum in London, England Travel
Tate Modern Tate Modern, London Art Gallery in London, England Travel
Principle of keyword selection:
(Delaney, 2017; Google, 2017)
8. ENTER 2018 Research Track Slide Number 8
Methodology:
Analytical Procedures
• Autoregressive integrated moving average (ARIMA):
(p,d,q)(P,D,Q)m model:
Φ(Bm)ϕ(B)(1 - Bm)D(1 - B)dyt = c+Θ(Bm)θ(B)ϵt,
where B is the backshift operator;
Φ(x) and Θ(x) are polynomials of orders P and Q, respectively;
ϕ(x) and θ(x) are polynomials of orders p and q, respectively;
ϵt is a white noise process with mean zero and variance σ2
• ARIMA with explanatory variable (ARIMAX)
9. ENTER 2018 Research Track Slide Number 9
Preliminary findings
Attraction, free entrance Visits, 2016 Rank Overseas
visitors
R
British Museum 6,420,395 Primary 58% 0.496***
National Gallery 6,262,839 Primary 61% 0.417***
Tate Modern 5,839,197 Secondary 50% 0.700***
Natural History Museum 4,624,113 Secondary 48% 0.854***
Science Museum (Group) 3,245,750 Secondary 27% 0.809***
Victoria and Albert Museum 3,022,086 Secondary 47% 0.473***
National Portrait Gallery 1,949,330 Secondary 40% 0.642***
Tate Britain 1,081,542 Secondary 50% 0.678***
Imperial War Museum 1,011,172 Secondary 40% 0.652***
Horniman Museum (Excluding gardens) 791,507 Tertiary 4% 0.650***
V&A Museum of Childhood 436,911 Tertiary n/a 0.287**
Wallace Collection 427,755 Tertiary 40% 0.242**
***p<0.01, **p<0.05, *p<0.10
10. ENTER 2018 Research Track Slide Number 10
Preliminary findings
Attraction, free entrance Visits (2016) Overseas visits Rank R
British Museum 6,420,395 58% Primary 0.496***
***p<0.01, **p<0.05, *p<0.10
0
20
40
60
80
100
120
0
100000
200000
300000
400000
500000
600000
700000
800000
900000
British Museum
Visits Search
Before Trip During Trip After Trip
11. ENTER 2018 Research Track Slide Number 11
Preliminary findings
***p<0.01, **p<0.05, *p<0.10
0
20
40
60
80
100
120
0
100000
200000
300000
400000
500000
600000
700000
Natural History Museum
Visits Search
Attraction, free entrance Visits (2016) Overseas visits Rank R
Natural History Museum 4,624,113 48% Secondary 0.854***
Before Trip During Trip After Trip
12. ENTER 2018 Research Track Slide Number 12
Preliminary findings
***p<0.01, **p<0.05, *p<0.10
Attraction, free entrance Visits, 2016 Rank Overseas
visitors
R
V&A Museum of Childhood 436,911 Tertiary n/a 0.287**
0
20
40
60
80
100
120
0
100000
200000
300000
400000
500000
600000
V&A
Total Vistis Online Search
13. ENTER 2018 Research Track Slide Number 13
Conclusion
• Identified relationships confirm the trend of decision making for
attractions to be done immediately before and during the trip
• The finding provide statistical proof on the difference in information
search for the three types of attractions
Theoretical Contributions
Practical Implications
• Information search patterns are confirmed to be an important
predictor of tourist decision to visit museum
• The new model is expected to become a tool for generation of
reliable forecasts on the number of visitors to museums
14. ENTER 2018 Research Track Slide Number 14
Conclusion
Limitations
• Higher frequency data would provide more detailed insights and
generate better forecasts
• More research is needed to explore the trend in different contexts and
different types of attractions
Future Research
• Search and visitor arrival data, aggregated to monthly view, do
not allow to identify the particular moment, when information
search occurs
• The difference in tourist behaviour does not allow to generalise
results to other destinations or target markets.
16. ENTER 2018 Research Track Slide Number 16
References
Artola, C., Pinto, F., & Pedraza, P. D. (2015). Can internet searches forecast tourism inflows? International Journal of Manpower, 36(1), 103-116.
Bangwayo-Skeete, P. F., & Skeete, R. W. (2015). Can Google data improve the forecasting performance of tourist arrivals? Mixed-data sampling approach.
Tourism Management, 46, 454-464.
Choi, H., & Varian, H. (2012). Predicting the present with Google Trends. Economic Record, 88(s1), 2-9.
Delaney, L. (2017). Monthly Museums and Galleries visits. Department for Digital, Culture, Media & Sport. Retrieved from:
https://www.gov.uk/government/statistical-data-sets/museums-and-galleries-monthly-visits
Google. (2017). Google Trends. Retrieved from https://trends.google.com/
Huang, X., Zhang, L., & Ding, Y. (2017). The Baidu Index: Uses in predicting tourism flows –A case study of the Forbidden City. Tourism Management, 58,
301-306.
Kadir, S. N., Tahir, N. M., Yassin, I. M., & Zabidi, A. (2014). Malaysian tourism interest forecasting using nonlinear auto-regressive moving average
(NARMA) model. Paper presented at the Wireless Technology and Applications (ISWTA), 2014 IEEE Symposium on.
Li, X., Pan, B., Law, R., & Huang, X. (2017). Forecasting tourism demand with composite search index. Tourism Management, 59, 57-66.
London & Partners (2015). London. Tourism Report 2014-2015. Retrieved October 01, 2016 fromhttp://files.londonandpartners.com/l-and-p/assets/our-
insight-london-tourism-review-2014-15.pdf
Önder, I. (2017). Forecasting tourism demand with Google trends: Accuracy comparison of countries versus cities. International Journal of Tourism
Research, doi:10.1002/jtr.2137
Pan, Wu, D. C., & Song, H. (2012). Forecasting hotel room demand using search engine data. Journal of Hospitality and Tourism Technology, 3(3), 196-210.
Park, S., Lee, J., & Song, W. (2017). Short-term forecasting of Japanese tourist inflow to South Korea using Google trends data. Journal of Travel and
Tourism Marketing, 34(3), 357-368.
Song, H., Witt, S. F., & Li, G. (2008). The advanced econometrics of tourism demand. NY: Routledge.
Xiang, Z., & Pan, B. (2011). Travel queries on cities in the United States: Implications for search engine marketing for tourist destinations. Tourism
Management, 32(1), 88-97.
Yang, X., Pan, B., Evans, J. A., & Lv, B. (2015). Forecasting Chinese tourist volume with search engine data. Tourism Management, 46, 386-397.
Yang, Y., Pan, B., & Song, H. (2014). Predicting hotel demand using destination marketing organization’s web traffic data. Journal of Travel Research, 53(4),
433-447
Editor's Notes
Technology allows to collect real time, high frequency data
In the recent decade proliferation of PCs and Internet allows to identify trends, relevant for the societies
Inmost cases. Information search precedes action or decision to buy
Information search indicates interest or desire, but not yet the readiness to buy
So that decision to choose is influenced by multiple external factors
Previous studies outline that the demand with online search trends can be overestimated
Because of complexity of tourist behaviour and multiple factors that affect it
Because search query does not always illustrate the object under investigation
The disadvantage: no guarantee that all the relevant SQ are included
However, attribution of a museum to a travel category incorporates not only the combination of 2 words, but other relevant ss