On the Inability of Markov Models to Capture Criticality in Human Mobility

  • Vaibhav KulkarniEmail author
  • Abhijit Mahalunkar
  • Benoit Garbinato
  • John D. Kelleher
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11729)


We examine the non-Markovian nature of human mobility by exposing the inability of Markov models to capture criticality in human mobility. In particular, the assumed Markovian nature of mobility was used to establish an upper bound on the predictability of human mobility, based on the temporal entropy. Since its inception, this bound has been widely used for validating the performance of mobility prediction models. We show that the variants of recurrent neural network architectures can achieve significantly higher prediction accuracy surpassing this upper bound. The central objective of our work is to show that human-mobility dynamics exhibit criticality characteristics which contributes to this discrepancy. In order to explain this anomaly, we shed light on the underlying assumption that human mobility characteristics follow an exponential decay that has resulted in this bias. By evaluating the predictability on real-world datasets, we show that human mobility exhibits scale-invariant long-distance dependencies, bearing resemblance to power-law decay, contrasting with the initial Markovian assumption. We experimentally validate that this assumption inflates the estimated mobility entropy, consequently lowering the upper bound on predictability. We demonstrate that the existing approach of entropy computation tends to overlook the presence of long-distance dependencies and structural correlations in human mobility. We justify why recurrent-neural network architectures that are designed to handle long-distance dependencies surpass the previously computed upper bound on mobility predictability.


Predictability limits Human-mobility Criticality 



This research work was partially supported by the Swiss National Science Foundation grant 157160. This research was also supported by the ADAPT Research Centre, funded under the SFI Research Centres Programme (Grant 13/ RC/2106) and is co-funded under the European Regional Development Funds. The research was also supported by an IBM Shared University Research Award.


  1. 1.
    Barabasi, A.L.: The origin of bursts and heavy tails in human dynamics. Nature 435(7039), 207 (2005)CrossRefGoogle Scholar
  2. 2.
    Bialek, W., Tishby, N.: Predictive information. arXiv preprint cond-mat/9902341 (1999)Google Scholar
  3. 3.
    Chang, S., et al.: Dilated recurrent neural networks. In: NIPS (2017)Google Scholar
  4. 4.
    Chomsky, N.: On certain formal properties of grammars. Inf. Control 2(2), 137–167 (1959)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Cuttone, A., Lehmann, S., González, M.C.: Understanding predictability and exploration in human mobility. EPJ Data Sci. 7(1), 2 (2018)CrossRefGoogle Scholar
  6. 6.
    Gambs, S., Killijian, M.O., del Prado Cortez, M.N.: Next place prediction using mobility Markov chains. In: Proceedings of the First Workshop on Measurement, Privacy, and Mobility, p. 3. ACM (2012)Google Scholar
  7. 7.
    Gerchinovitz, S., Ménard, P., Stoltz, G.: Fano’s inequality for random variables. arXiv preprint arXiv:1702.05985 (2017)
  8. 8.
    Grassberger, P.: Entropy estimates from insufficient samplings. arXiv preprint physics/0307138 (2003)Google Scholar
  9. 9.
    Grossberg, S.: Recurrent neural networks. Scholarpedia 8(2), 1888 (2013)CrossRefGoogle Scholar
  10. 10.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–80 (1997)CrossRefGoogle Scholar
  11. 11.
    Ikanovic, E.L., Mollgaard, A.: An alternative approach to the limits of predictability in human mobility. EPJ Data Sci. 6(1), 12 (2017)CrossRefGoogle Scholar
  12. 12.
    Khandelwal, U., He, H., Qi, P., Jurafsky, D.: Sharp nearby, fuzzy far away: how neural language models use context. arXiv preprint arXiv:1805.04623 (2018)
  13. 13.
    Krumme, C., Llorente, A., Cebrian, M., Moro, E., et al.: The predictability of consumer visitation patterns. Sci. Rep. 3, 1645 (2013)CrossRefGoogle Scholar
  14. 14.
    Laurila, J.K., et al.: The mobile data challenge: big data for mobile computing research. In: Pervasive Computing, No. EPFL-CONF-192489 (2012)Google Scholar
  15. 15.
    Lesne, A., Blanc, J.L., Pezard, L.: Entropy estimation of very short symbolic sequences. Phys. Rev. E 79(4), 046208 (2009)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Lin, H.W., Tegmark, M.: Critical behavior from deep dynamics: a hidden dimension in natural language. arXiv preprint arXiv:1606.06737 (2016)
  17. 17.
    Lin, H.W., Tegmark, M.: Critical behavior in physics and probabilistic formal languages. Entropy 19(7), 299 (2017)CrossRefGoogle Scholar
  18. 18.
    Lu, X., Wetter, E., Bharti, N., Tatem, A.J., Bengtsson, L.: Approaching the limit of predictability in human mobility. Sci. Rep. 3, 2923 (2013)CrossRefGoogle Scholar
  19. 19.
    Massey Jr., F.J.: The Kolmogorov-Smirnov test for goodness of fit. J. Am. Stat. Assoc. 46(253), 68–78 (1951)CrossRefGoogle Scholar
  20. 20.
    Merity, S., Xiong, C., Bradbury, J., Socher, R.: Pointer sentinel mixture models. CoRR abs/1609.07843 (2016)Google Scholar
  21. 21.
    Mokhtar, S.B., et al.: PRIVA’MOV: analysing human mobility through multi-sensor datasets. In: NetMob 2017 (2017)Google Scholar
  22. 22.
    Newman, M.E.: Power laws, pareto distributions and Zipf’s law. Contemp. Phys. 46(5), 323–351 (2005)CrossRefGoogle Scholar
  23. 23.
    Pérez-Cruz, F.: Kullback-Leibler divergence estimation of continuous distributions. In: 2008 IEEE International Symposium on Information Theory, pp. 1666–1670 (2008)Google Scholar
  24. 24.
    Prelov, V.V., van der Meulen, E.C.: Mutual information, variation, and Fano’s inequality. Probl. Inf. Trans. 44(3), 185–197 (2008)CrossRefGoogle Scholar
  25. 25.
    Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)CrossRefGoogle Scholar
  26. 26.
    Smith, G., Wieser, R., Goulding, J., Barrack, D.: A refined limit on the predictability of human mobility. In: 2014 IEEE International Conference on Pervasive Computing and Communications (PerCom), pp. 88–94. IEEE (2014)Google Scholar
  27. 27.
    Song, C., Qu, Z., Blumm, N., Barabási, A.L.: Limits of predictability in human mobility. Science 327(5968), 1018–1021 (2010)MathSciNetCrossRefGoogle Scholar
  28. 28.
    Song, L., Kotz, D., Jain, R., He, X.: Evaluating next-cell predictors with extensive Wi-Fi mobility data. IEEE Trans. Mob. Comput. 5(12), 1633–1649 (2006)CrossRefGoogle Scholar
  29. 29.
    Storer, J.A.: Data Compression: Methods and Theory. Computer Science Press, Inc., Rockville (1987)Google Scholar
  30. 30.
    Yan, X.Y., Han, X.P., Wang, B.H., Zhou, T.: Diversity of individual mobility patterns and emergence of aggregated scaling laws. Sci. Rep. 3, 2678 (2013)CrossRefGoogle Scholar
  31. 31.
    Zhao, Z.D., Cai, S.M., Lu, Y.: Non-Markovian character in human mobility online and offline. Chaos: Interdisc. J. Nonlinear Sci. 25(6), 063106 (2015)CrossRefGoogle Scholar
  32. 32.
    Zheng, Y., Xie, X., Ma, W.Y.: Geolife: a collaborative social networking service among user, location and trajectory. IEEE Data Eng. Bull. 33(2), 32–39 (2010)Google Scholar
  33. 33.
    Zilly, J.G., Srivastava, R.K., Koutník, J., Schmidhuber, J.: Recurrent highway networks. In: ICML (2017)Google Scholar
  34. 34.
    Ziv, J., Lempel, A.: Compression of individual sequences via variable-rate coding. IEEE Trans. Inf. Theory 24(5), 530–536 (1978)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.UNIL-HEC LausanneLausanneSwitzerland
  2. 2.ADAPT Research CenterTechnological University DublinDublinIreland

Personalised recommendations