GKB: Geodemographics Knowledge Base

The MRS Census and GeoDems group champions new thinking and new talent; one area they have been particularly impressed with is the CDRC Masters Dissertation Scheme (MDS)

This programme offers an exciting opportunity to link students on Masters courses with leading retail companies on projects which are important to the retail industry. The scheme provides the opportunity to work directly with an industrial partner and to link students’ research to important retail and ‘open data’ sources. The project titles are devised by retailers and are open to students from a wide range of disciplines.

MRS CGG are proud to have been granted permission to publish abstracts from the dissertations and we are sure the students have a great future ahead of them.

This abstract is by Siyao Li

Title: Study on the Arrival Profile of Large Public Events

Academic Institution: University College London

Industry Sponsor: GHD

To prevent hurt caused by crowd disasters at large public events, it is crucial to know the audience's arrival distribution since the shape and peak of the distribution would have a big impact on crowd management and venue operations. This project studies the arrival profile of 23 large events from 4 sport types (football, rugby, tennis and golf) held in 6 stadiums and tend to answer:

1. Does the arrival profile follow any general distribution?
2. What are the key factors that cause differences in the arrival profiles?


1. Arrival Distribution
- Arrival trend
- ECDF plots
- K-S test
- Distribution fit

2. Demographic Profiles
- Home location
- Travel distance

3. Mobility Studies
- Average time spent nearby
- Stop point detection
- Hexagon cluster map

Zoning and Data Cleaning

/blog/Fig 1.JPG


1. Arrival Distribution

1.1 Arrival Trend 

Fig 2

Time record of users first being discovered to be inside of each zone of the stadium were extracted and plotted. On a general view, the arrival shape for football and rugby looked similar, whereas the trend seemed more volatile for tennis and golf.

1.2 ECDF Plot

/blog/fig 3.JPG

For EPL games held in the same venue, the shape of arrival distribution was alike, regardless of opponent teams, day of the week or start time. However, arrival rate differed for football matches held in different stadiums. The general arrival trend seemed to be earlier in international competitions and decisive games such as the finals, compared with domestic and preliminary rounds.

1.3 Distribution Fitting

Fig 4

/blog/fig 5.JPG Fig 6

Arrival data lists were fitted to a range of continuous distributions supported in `scipy.stats`. 5 best-fit ones with the smallest RSS aggregated by sport type and displayed in a word cloud.

Distributions for football and rugby were close to theoretical Johnson’s SU and Burr capture a general trend for tennis and golf. Peak-time arrivals for all events seemed to be underestimated.

2. Demographic Profiles

/blog/fig 7.JPG

Demographic profiles for football and rugby audience were more diverse than Wimbledon and Royal St George’s Golf Club. This was also reflected in the box-violin plot that travel distance for Wimbledon and Royal St George’s were much shorter compared with other stadiums.

3. Mobility Studies

/blog/fig 8.JPG

People spent 15-35 minutes on average in surrounding areas for EPL games held in Emirates and Old Trafford Stadium, and in Wimbledon Championships, whereas a bit longer for the Open Golf and Rugby matches. Stops mostly clustered near car park and transport stations, which calls out the importance of traffic management, as traffic jams would increase the risk of late-arrivals clusters.


1. Johnson’s SU and Burr were suggested as a good representation of arriving trend for football and rugby, tennis and golf, respectively.

2. Arrival distribution was alike for the same type of sports events held in the same venue; The general arrival trend seemed to be earlier in decisive games than preliminary rounds;

3. More late arrivals for football matches held during the ERP period.

4. Audience’s demographic profiles were more diverse in team competitions than games with individual players.

5. Facilities around the venue have an impact on arrival behaviours.



Geodemographics - blogs and resources

Visit the Geodemographics Knowledge Base (GKB) for expert blogs and links to useful sources of geodemographic data and knowledge.

Visit the website A white arrowA black arrow

Get the latest MRS news

Our newsletters cover the latest MRS events, policy updates and research news.