Judge Me in Context: A Telematics-Based Driving Risk Prediction Framework in Presence of Weak Risk Labels
This work addresses driving safety for applications like insurance planning, but it is incremental as it builds on existing telematics-based methods by incorporating contextual information.
The paper tackles driving risk prediction by maximizing the use of telematics and contextual data, such as road-type, to build a risk classifier with weak labels like traffic citations, and demonstrates its usefulness through analysis on real-world data from multiple U.S. cities.
Driving risk prediction has been a topic of much research over the past few decades to minimize driving risk and increase safety. The use of demographic information in risk prediction is a traditional solution with applications in insurance planning, however, it is difficult to capture true driving behavior via such coarse-grained factors. Therefor, the use of telematics data has gained a widespread popularity over the past decade. While most of the existing studies leverage demographic information in addition to telematics data, our objective is to maximize the use of telematics as well as contextual information (e.g., road-type) to build a risk prediction framework with real-world applications. We contextualize telematics data in a variety of forms, and then use it to develop a risk classifier, assuming that there are some weak risk labels available (e.g., past traffic citation records). Before building a risk classifier though, we employ a novel data-driven process to augment weak risk labels. Extensive analysis and results based on real-world data from multiple major cities in the United States demonstrate usefulness of the proposed framework.