European Actuarial Journal

, Volume 8, Issue 2, pp 383–406 | Cite as

Feature extraction from telematics car driving heatmaps

  • Guangyuan Gao
  • Mario V. WüthrichEmail author
Original Research Paper


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 (autoencoders) 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).


Telematics car driving data Driving styles Unsupervised learning Pattern recognition Image recognition Bottleneck neural network Autoencoder Singular value decomposition Principal component analysis K-means algorithm Kullback–Leibler divergence 



Guangyuan Gao: Financially supported by the Social Science Fund of China (Grant no. 16ZDA052) and MOE National Key Research Bases for Humanities and Social Sciences (Grant no. 16JJD910001).


  1. 1.
    Ayuso M, Guillen M, Pérez-Marín AM (2016). Telematics and gender discrimination: some usage-based evidence on whether men’s risk of accidents differs from women’s. Risks 4/2, article 10Google Scholar
  2. 2.
    Gao G, Meng S, Wüthrich MV (2018) Claims frequency modeling using telematics car driving data. Scand Actuarial. (to appear)CrossRefGoogle Scholar
  3. 3.
    Hainaut D (2018) A neural-network analyzer for mortality forecast. ASTIN Bull 48(2):481–508MathSciNetCrossRefGoogle Scholar
  4. 4.
    Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning. Data mining, inference, and prediction, 2nd edn. Springer Series in Statistics, BerlinzbMATHGoogle Scholar
  5. 5.
    Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313:504–507MathSciNetCrossRefGoogle Scholar
  6. 6.
    Kramer MA (1991) Nonlinear principal component analysis using autoassociative neural networks. AIChE J 37(2):233–243CrossRefGoogle Scholar
  7. 7.
    Liou CY, Cheng CW, Liou JW, Liou DR (2014) Autoencoders for words. Neurocomputing 139:84–96CrossRefGoogle Scholar
  8. 8.
    Verbelen R, Antonio K, Claeskens G (2018) Unraveling the predictive power of telematics data in car insurance pricing. J Roy Stat Soc Ser C (Appl Stat) (to appear)Google Scholar
  9. 9.
    Weidner W, Transchel FWG, Weidner R (2016) Classification of scale-sensitive telematic observables for riskindividual pricing. Eur Actuar J 6(1):3–24MathSciNetCrossRefGoogle Scholar
  10. 10.
    Weidner W, Transchel FWG, Weidner R (2016) Telematic driving profile classification in car insurance pricing. Ann Actuar Sci 11(2):213–236CrossRefGoogle Scholar
  11. 11.
    Wüthrich (2017) Covariate selection from telematics car driving data. Eur Actuar J 7(1):89–108MathSciNetCrossRefGoogle Scholar
  12. 12.
    Wüthrich MV, Buser C (2016) Data analytics for non-life insurance pricing. SSRN Manuscript ID 2870308. Version October 25, 2017Google Scholar

Copyright information

© EAJ Association 2018

Authors and Affiliations

  1. 1.Center for Applied Statistics and School of StatisticsRenmin University of ChinaBeijingChina
  2. 2.Department of MathematicsETH Zurich, RiskLabZurichSwitzerland

Personalised recommendations