How to track, analyse and understand tourist flows in a city, with a view to adapting services to tourists’ changing habits?
Paris has long been one of the world’s most popular tourist destinations, and tourists account for a significant portion of the people in the city at any point in time. Tourists also contribute a substantial circa €40 billion a year to its finances, and this sector is enjoying buoyant growth on the back of strong demand from emerging countries. International tourism is expected to continue to grow at a sturdy 5% or so a year.
In light of the stakes, Paris City Council has mapped out a 59-initiative master plan to develop tourism. In practice, those initiatives add up to improving tourist reception facilities and providing a range of novel products and services tailored to the foreigners visiting the city.
Enhancing a city’s appeal and upgrading its tourist attractions also involves understanding tourist flows. For example, it is important to know what countries visitors come from, which neighbourhoods they prefer, how they travel around the city, what routes they follow, when they travel, their profiles, how many tourists return to the city, and what they visit the second time.
Today, habits, wants and needs are evolving faster than the tools we have to analyse them. Most existing studies are based on surveys providing macroeconomic figures such as tourist footfall or, conversely, qualitative studies shedding no light on mass effects.
Data-centric analytics should help to fine-tune deals to tourists’ requirements, or even tailor deals individually, before and after trips. They should also help to assess policies aimed at improving tourist reception and Paris’ appeal more rapidly.
Use case and experimentation field
Business opportunities for the stakeholders
The discussions and experiments in this challenge will broach the issues from three angles:
1. Enlightening decisions on neighbourhood planning
- The goal, here, is to understand how people living in a given neighbourhood interact with the area. This will involve analysing the existing situation in light of studies based on macroeconomic data and then factoring in dynamic data (residents’ habits, local lifestyles, social interconnections), to inform decisions on how to develop unused space (e.g. with shops, day-care centres, offices, etc.)
The experiment field could be a neighbourhood in the midst of widespread redevelopment, such as Clichy-Batignolles
2. Attracting new businesses
- This will involve furnishing data analysis to help new shops (e.g. bakeries) or other businesses (e.g. day-care centres or office buildings) to fine-tune their approach. The goal is to home in on the type of business that will thrive by analysing accurate and consistent data to map out a business’ precise catchment area
This experiment could target an area embarking on an upswing, such as the 18th, 19th and 20th arrondissements in Paris, or cities skirting it such as Saint Ouen, Montreuil and Asnières sur Seine
3. Understanding and assessing the impact of permanent or temporary facilities on travel patterns (walking, cycling, etc.) and traffic
- The goal, here, is to analyse data reflecting motor-vehicle, bicycle and pedestrian flows to inform decisions that will encourage soft mobility (cycling, walking) and ease motor-vehicle flows
The partners will supply the following data to conduct the experiment in this challenge:
SFR: Travel-related data from mobile devices (technical data from GSM antennas) for a representative sample (approx. 30% of the population), covering uninterrupted periods (24/7) in France (locals and foreigners)
Mastercard: Anonymised data from its transaction records, i.e. transaction amounts, user profiles, payment methods (contactless, smartphone or touchpad), geolocations (merchant codes), times and average purchases
Cisco: Data from the sensors it installed in Place de la Nation in September 2015 to assess the impact of future developments. It has since gathered a substantial amount of data and will share it with the startups working on this challenge
INSEE: Data on its IRIS statistical information clusters, in this case macroeconomic data that may complete the other available data set
UBER: qualitative data from foreign users’ travel behavior
Suez: help cities fine-tune their initiatives to improve tourist transport and services
SFR: extract value from mobile data, market solutions to tour operators and communities, and jointly develop solutions combining data from various sources
RATP Dev: use the solution to reviews available tourist bus services and size future services, then possibly use the solution on its conventional bus lines
Cisco: develop predictive analysis solutions jointly with startups
Paris City Council: enhance Paris’ appeal and tourist amenities following a decline in tourist numbers
The startup: develop a new service, leveraging the large amount of data supplied by the partners listed above
To solve this challenge, AiD-Add Intelligence to data, the selected startup, has developed an application, “Trend Shaker”, that mutualizes a variety of datasets including roaming data from SFR, cross border transactions data from Mastercard, as well as data from foreign users Uber. This enables the user of the application to understand, analyze and monitor how and where tourists travel in Paris, where and on what they spend money – all that at specific times of the day. It is therefore a powerful tool both for tourism department of the city of Paris, Paris’ tourist office as well as department stores, hotels, tourist sites and any service providers to the benefit of tourists in Paris.
Implementation of an interface of data analysis and visualization with
- 3 different data sets mutualized and integrated in the solution
- 20 main nationalities of tourists analyzed