Problem: Public transportation is a crucial component to every city, and a poor management of this resource can greatly affect citizens day-to-day lives by creating traffic, pollution, and population satisfaction in general.

Solution: The team presented a machine learning model capable of predicting mobility rates in Porto, using anonymized Wi-Fi data and geospatial characteristics. The solution aims to optimize public transport, protecting citizens’ privacy through techniques such as hashing and differential privacy.

Problem: Managing a city’s Wi-Fi resources is a challenging but vital task for public benefit, like improving connections in crowded areas or identifying places that need Wi-Fi access. However, handling this data also poses privacy risks if not managed correctly.

Solution: Development of a probabilistic anonymization solution applied to geolocation data. The project addressed re-identification risks and preserved the usefulness of data for predictive analysis, highlighting urban trajectories.

Problem: A city’s WiFi system offers benefits to residents, but the data collected can pose risks to user privacy. Balancing data protection with effective analysis for the community is a difficult challenge.

Solution: The team focused on anonymizing Wi-Fi data using the Faker library and created a predictive model to estimate session counts. The solution balanced privacy and analytical potential, standing out for its simplicity and effectiveness.

Problem: As digital transition grows worldwide, more personal data is stored and analyzed by various organizations. This raises an important issue: how to balance analysis for better services with privacy.

Solution: Creation of a repeatable anonymization platform, which combines flexibility and consistency in the management of sensitive data, allowing analysis while preserving privacy.