Challenge / Goal
Lisbon, the capital city of Portugal, has been grappling with a significant traffic problem that poses challenges to residents, commuters, and policymakers alike. The city experiences severe congestion during peak hours, particularly in the city center and major thoroughfares, leading to slow-moving or stationary traffic. This congestion is exacerbated by inadequate infrastructure that struggles to accommodate the growing number of vehicles. Additionally, the public transportation system, while extensive, faces challenges in providing a viable alternative to private vehicles, with delays, overcrowding, and limited coverage discouraging its use. The limited availability of parking spaces further adds to the problem, as drivers circle around in search of spots, contributing to congestion. The city's unique urban layout, characterized by narrow streets, steep hills, and a mix of historical and modern architecture, presents additional obstacles for traffic management. Moreover, the influx of tourists exacerbates the issue, with tourist buses, rental cars, and unfamiliar pedestrians further congesting the roads. Although efforts have been made to address these challenges, including expanding public transportation and promoting alternative modes of transport, overcoming Lisbon's traffic problem requires a comprehensive approach involving infrastructure development, urban planning, and continued promotion of sustainable transportation options.
The goal of this initiative is to create new models either to predict or to generate viable alternatives for illegal parking in the city of Lisbon
Solution
The Illegal Parking Score (IPS), an indicator that assesses the risk of illegal parking. The IPS is calculated based on the conditional probability of a parking infraction occurring given a set of conditions, including the road segment, period of the day, type of day, temperature, and precipitation.
To facilitate decision-making, we have developed a Dashboard for the IPS simulator, a tool that provides predictions on the risk of illegal parking based on user-defined spatiotemporal and weather conditions.
Want to learn more about the lessons learned, financial details and results?
Log in