Challenge data

As the 2025 season has been exceptionally extended into 2026, the leaderboard shown reflects exclusively the 2025 results.

Description

Competitive challenge

Humanities

Industrial

Regression

Time series

Tabular

10MB to 1GB

Basic level

Dates

Started on Jan. 13, 2026

Challenge context

#### Egis
**Egis** is an international consulting, engineering and operating group. 
With more than 19,000 employees, it is present in over 100 countries and operates in various sectors such as transport infrastructure, construction, water, environment and energy. 
**Egis** stands out for its technical expertise and its ability to carry out large-scale projects, with a focus on sustainable development and innovation. 
The group offers integrated solutions ranging from design to operation, including consultancy and project management.

#### datacraft
This challenge was designed with the support of **datacraft**.

**datacraft** is a unique Club model, inspired by apprenticeship, designed to enable data scientists and data engineers to learn from their peers and help companies accelerate their AI projects. The first Club opened in Paris in February 2020. Today, it includes 41 major corporate members (Accor, Airbus, BNP Paribas, Bouygues, Crédit Agricole, Egis, L’Oréal, but also AP-HP, CNES, the French Navy...), startups, and more than 600 researchers and freelance AI experts.

Website : https://datacraft.paris

Challenge goals

Egis contributes to the operation of on-street parking enforcement for several cities in France and abroad.
Camera-equipped vehicles take photos of parked vehicles.
Then, on the basis of the licence plate number, geolocation and time stamp, a process is initiated to check the validity of the parking and, if necessary, issue a post-parking charge. Egis develops and provides the software that supports this process.
In particular, one of the modules of this solution displays numerous activity-related indicators.
The volume of data collected is therefore considerable.

We are convinced that the analysis of this data would optimise the operating activity on the one hand and would reduce the infringement rate.

We therefore suggest developing a Machine Learning model with the aim of Identifying the zones / times where there are the most offences and optimise the routes of parking enforcement vehicles accordingly.
This would make it possible, on the one hand, to direct controls where they are most relevant and, on the other hand, to optimise the fleet of vehicles required.
For information, the service operator is required to check each paid parking space twice a day on average.

Data description

Benchmark description

Files

Files are accessible when logged in and registered to the challenge

The challenge provider

Consulting, construction engineering and operating company

PROVIDER WEBSITE

Congratulation for the winners of the challenge

1 Christophe Leroux
2 Antoine Li
3 Martin Deldicque

Challenge Data

Predict parking violations!
by Egis

Description

Dates

Challenge context

Challenge goals

Data description

Benchmark description

Files

The challenge provider

Congratulation for the winners of the challenge

Challenge Data

Predict parking violations! by Egis

Description

Dates

Challenge context

Challenge goals

Data description

Benchmark description

Files

The challenge provider

Congratulation for the winners of the challenge

Predict parking violations!
by Egis