Publication Date

Spring 5-18-2015

Degree Type

Master's Project

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Robert Chun

Second Advisor

T. Y. Lin

Third Advisor

Chris Tseng

Abstract

For automobile insurance firms, telemetric analysis represents a valuable and growing way to identify the risk associated with each driver. The pricing decisions of an insurer are best accounted for if they are made considering the driver’s behavior instead of just the vehicle characteristics and the best way to understand a driver’s behavior is to leverage the telemetric analysis. Decisions made on such factors can eventually lead to increased premium or reduced liability for unsafe or reckless drivers and can also help in transitioning the burden to the policies that lead to increased liability.

The dataset provided for this project by AXA has 50000 trips from anonymized drivers. A small and varied number of false trips (trips that do not belong to the particular driver of interest) are accounted for each driver. These trips are picked from drivers not given in the dataset, in order to avoid similarity with the given drivers. Neither the number of such false trips, nor the trips with a labeled set of true positives are given. However, it is given that most of the trips do belong to the particular driver of interest. The goal of this project is to develop a driving signature of each driver and identify the trips which are not driven by the particular driver of interest by predicting a probability for each trip that is accounted for the driver.

Share

COinS