Feature Extraction from Telematics Car Driving Heatmaps
16 Pages Posted: 16 Nov 2017
Date Written: November 13, 2017
Abstract
Insurance companies have started to collect high-frequency GPS car driving data to analyze the driving styles of their policyholders. In previous work, we have introduced speed and acceleration heatmaps. These heatmaps were categorized with the K-means algorithm to differentiate varying driving styles. In many situations it is useful to have low-dimensional continuous representations instead of unordered categories. In the present work we use singular value decomposition and bottleneck neural networks for principal component analysis. We show that a two-dimensional representation is sufficient to re-construct the heatmaps with high accuracy (measured by Kullback-Leibler divergences).
Keywords: Telematics car driving data, driving styles, unsupervised learning, pattern recognition, image recognition, bottleneck neural network, singular value decomposition, principal component analysis, Kullback-Leibler divergence
JEL Classification: G22, G28
Suggested Citation: Suggested Citation