The core of our methodology

What is the Mytraffic technology based on?

Mytraffic works with GPS data from various mobile applications on which it applies its technology and algorithms.

The applications target either the general public or differentiated target audiences. For example, in terms of press, we have the general public press (Téléloisir, Télé Star, etc.), the women's press (Gala, Closer, etc.) and the men's press (Auto Plus, etc.), but also the regional press (Nice Matin, etc.).

The navigation applications allow us to have rich data by regularly reporting points related to the importance of the geolocation functionality for the application.

When we receive the data, we make sure that it is representative of the territory, time and socio-demographics. We correct any possible biases that may exist in order to obtain a stable panel over time.

What is the granularity of our data?

We track more than 200 billions GPS points per year in all our countries, which represents +120 GPS positions per day per user. We verify day after day that our user panel is representative of all socio-demographic categories and over the entire territory we cover.

Our data has a geographical accuracy of 5 to 10 metres, making it much more accurate than data from mobile operators, relayed by network antennas, which have an accuracy of around 100 to 200 metres.

How does Mytraffic combine its algorithms with physical counting?

We couple our geolocation data with physical counts and measurements to ensure that the adjustment of our raw data is as close as possible to the field experience.

For example, for address-based analysis we will count passers-by on the street, for shopping centres we post people to count people at each entrance. We supplement this with continuously collected sensor data.

We then couple these field measurements with our massive data to scale up our algorithms to the scale of Europe, moving from the discrete nature of the field measurement to statistics covering the entire territory.

These measurements are regularly updated to ensure that our algorithms do not become disconnected from the reality on the ground.

Our algorithms run daily for intermediate daily data and once a month to calculate the final statistics presented in the product.