Subventions et des contributions :

Subvention ou bourse octroyée s'appliquant à plus d'un exercice financier (2017-2018 à 2018-2019).

Since the end of 2013, Intact Insurance offers usage-based car insurance programs designed to leveragex000D
data-driven technologies and improve insurance products. Under these programs, Intact collects driving datax000D
from customers using either a GPS dongle connected to the car on-board computer or a smartphonex000D
application. This data is used to characterize driving behavior and to detect risky events. In order to pre-processx000D
this massive amount of data collected, a map-matching algorithm needs to be implemented. Map matching isx000D
the process of estimating a user's position on a road segment. Concretely, GPS positions are provided only inx000D
terms of latitude and longitude and are not linked spatially to the road network. This is particularly of concernx000D
in urban centers, where tall buildings can completely block GPS signals or create spurious signals, leading tox000D
positional noise of several meters in magnitude. If the goal is to determine travelling patterns, then it isx000D
necessary to explicitly match each trip to the travelled network links. Although several map-matchingx000D
procedures have been developed in the literature, no formal comparison exists in terms of accuracy andx000D
computational speed. These issues are extremely important for Intact Insurance, who needs to find the optimalx000D
trade-off between computational cost and precision. Furthermore, the performance of existing methods mayx000D
vary greatly depending on the type of environment (urban, suburban, highways, etc.) and the use of a singlex000D
method might not be the optimal solution. Moreover, the combination of GPS and sensor data has been rarelyx000D
investigated in the context of big data; this could improve the map-matching accuracy but increases thex000D
computing complexity. Therefore, the objective of this research project is to: 1) evaluate the performance ofx000D
existing map-matching methods both in terms of efficiency and accuracy, 2) investigate the benefits ofx000D
combining GPS and sensor data in the map-matching accuracy, and 3) calibrate the optimal method(s) intox000D
Intact Insurance's analytical pipeline.