Modeling the Temporal Nature of Human Behavior for Demographics Prediction

  • Bjarke Felbo
  • Pål Sundsøy
  • Alex ‘Sandy’ Pentland
  • Sune Lehmann
  • Yves-Alexandre de Montjoye
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10536)

Abstract

Mobile phone metadata is increasingly used for humanitarian purposes in developing countries as traditional data is scarce. Basic demographic information is however often absent from mobile phone datasets, limiting the operational impact of the datasets. For these reasons, there has been a growing interest in predicting demographic information from mobile phone metadata. Previous work focused on creating increasingly advanced features to be modeled with standard machine learning algorithms. We here instead model the raw mobile phone metadata directly using deep learning, exploiting the temporal nature of the patterns in the data. From high-level assumptions we design a data representation and convolutional network architecture for modeling patterns within a week. We then examine three strategies for aggregating patterns across weeks and show that our method reaches state-of-the-art accuracy on both age and gender prediction using only the temporal modality in mobile metadata. We finally validate our method on low activity users and evaluate the modeling assumptions.

Keywords

Call Detail Records Mobile phone metadata Temporal patterns User modeling Demographics prediction 

References

  1. 1.
    Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. TPAMI 35(8), 1798–1828 (2013)CrossRefGoogle Scholar
  2. 2.
    Bengtsson, L., Lu, X., Thorson, A., Garfield, R., Von Schreeb, J.: Improved response to disasters and outbreaks by tracking population movements with mobile phone network data: a post-earthquake geospatial study in Haiti. PLoS Med. 8(8), e1001083 (2011)CrossRefGoogle Scholar
  3. 3.
    Chollet, F.: keras (2015). https://github.com/fchollet/keras
  4. 4.
    Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: Decaf: a deep convolutional activation feature for generic visual recognition. In: PMLR. arXiv arXiv:1310.1531 (2013)
  5. 5.
    Dong, Y., Yang, Y., Tang, J., Yang, Y., Chawla, N.V.: Inferring user demographics and social strategies in mobile social networks. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 15–24. ACM (2014)Google Scholar
  6. 6.
    Frias-Martinez, V., Frias-Martinez, E., Oliver, N.: A gender-centric analysis of calling behavior in a developing economy using call detail records. In: AAAI Spring Symposium: Artificial Intelligence for Development (2010)Google Scholar
  7. 7.
    Gal, Y.: A theoretically grounded application of dropout in recurrent neural networks. In: NIPS. arXiv arXiv:1512.05287 (2016)
  8. 8.
    Herrera-Yagüe, C., Zufiria, P.J.: Prediction of telephone user attributes based on network neighborhood information. In: Perner, P. (ed.) MLDM 2012. LNCS (LNAI), vol. 7376, pp. 645–659. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-31537-4_50 CrossRefGoogle Scholar
  9. 9.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  10. 10.
    Jahani, E., Sundsøy, P., Bjelland, J., Bengtsson, L., de Montjoye, Y.A., et al.: Improving official statistics in emerging markets using machine learning and mobile phone data. EPJ Data Sci. 6(1), 3 (2017)CrossRefGoogle Scholar
  11. 11.
    Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: Convolutional architecture for fast feature embedding. arXiv arXiv:1408.5093 (2014)
  12. 12.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: ICLR. arXiv arXiv:1412.6980 (2015)
  13. 13.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  14. 14.
    Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of ICML (2013)Google Scholar
  15. 15.
    de Montjoye, Y.-A., Quoidbach, J., Robic, F., Pentland, A.S.: Predicting personality using novel mobile phone-based metrics. In: Greenberg, A.M., Kennedy, W.G., Bos, N.D. (eds.) SBP 2013. LNCS, vol. 7812, pp. 48–55. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-37210-0_6 CrossRefGoogle Scholar
  16. 16.
    de Montjoye, Y.A., Rocher, L., Pentland, A.S.: bandicoot: a Python toolbox for mobile phone metadata. J. Mach. Learn. Res. 17(175), 1–5 (2016). http://jmlr.org/papers/v17/15-593.html MathSciNetMATHGoogle Scholar
  17. 17.
    News, I.: Mobile subscriptions near the 7 billion mark - does almost everyone have a phone? (2013). Accessed 5 Jan 2016. http://itunews.itu.int/en/3741-Mobile-subscriptions-near-the-78209billion-markbrDoes-almost-everyone-have-a-phone.note.aspx
  18. 18.
    Nielsen, M.A.: Neural Networks and Deep Learning. Determination Press (2015)Google Scholar
  19. 19.
    Sarraute, C., Blanc, P., Burroni, J.: A study of age and gender seen through mobile phone usage patterns in Mexico. In: ASONAM (2014)Google Scholar
  20. 20.
    Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: NIPS (2012)Google Scholar
  21. 21.
    Stuart, E., Samman, E., Avis, W., Berliner, T.: The data revolution: finding the missing millions. Overseas Development Institute (2015)Google Scholar
  22. 22.
    Theano Development Team: Theano: a Python framework for fast computation of mathematical expressions. arXiv arXiv:1605.02688 (2016)
  23. 23.
    United Nations: A world that counts - mobilising the data revolution for sustainable development (2014). UN Independent Expert Advisory Group on a Data Revolution for Sustainable DevelopmentGoogle Scholar
  24. 24.
    Wesolowski, A., Qureshi, T., Boni, M.F., Sundsøy, P.R., Johansson, M.A., Rasheed, S.B., Engø-Monsen, K., Buckee, C.O.: Impact of human mobility on the emergence of dengue epidemics in Pakistan. PNAS 112(38), 11887–11892 (2015)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Bjarke Felbo
    • 1
    • 3
  • Pål Sundsøy
    • 2
  • Alex ‘Sandy’ Pentland
    • 1
  • Sune Lehmann
    • 3
  • Yves-Alexandre de Montjoye
    • 1
    • 4
  1. 1.MIT Media LabMassachusetts Institute of TechnologyCambridgeUSA
  2. 2.Telenor ResearchOsloNorway
  3. 3.DTU ComputeTechnical University of DenmarkKgs. LyngbyDenmark
  4. 4.Department of Computing and Data Science InstituteImperial College LondonLondonUK

Personalised recommendations