Travel Time Prediction Based on Raw GPS Data
Name
Sander-Sebastian Värv
Abstract
With the ever growing pace of our everyday lives, time planning has gained a lot of im-portance. One of the key factors for time planning is to estimate the duration of moving from one place to another. Therefore, travel time prediction has become essential part of any logistics based business. This thesis is conducted in collaboration with Bolt, which is one of the leading ride hailing companies. This thesis is describing route based travel time prediction algorithm based on raw GPS data. The goal is to analyze each of the pre-processing steps and to develop a coherent method to predict arrival time based on GPS input data supplied by Bolt. Furthermore, route based method described in this thesis is validated by comparing it to two well-known and established methods.
Graduation Thesis language
English
Graduation Thesis type
Master - Computer Science
Supervisor(s)
Amnir Hadachi, Artjom Lind
Defence year
2019