Towards a boosted route planner using individual mobility models

Route planners generally return routes that minimize either the distance covered or the time traveled. However, these routes are rarely considered by people who move in a certain area systematically. Indeed, due to their expertise, they very often prefer different solutions. In this paper we provide an analytic model to study the deviations of the systematic movements from the paths proposed by a route planner. As proxy of human mobility we use real GPS traces and we analyze a set of users which act in Pisa and Florence province. By using appropriate mobility data mining techniques, we extract the GPS systematic movements and we transform them into sequences of road segments. Finally, we calculate the shortest and fastest path from the origin to the destination of each systematic movement and we compare them with the routes mapped on the road network. Our results show that about 30-35% of the systematic movements follow the shortest paths, while the others follow routes which are on average 7 km longer. In addition, we divided the area object of study in cells and we analyzed the deviations in the flows of systematic movements. We found that, these deviations are not only driven by individual mobility behaviors but are a signal of an existing common sense that could be exploited by a route planner.