Abstract
Using long-running panel data from the Household, Income and Labour Dynamics in Australia (HILDA) survey collected annually between 2001 and 2015, we aim to generate a sequence of events for individuals by processing real life trajectories one step at a time and predict what comes next. This is motivated by the need for understanding and predicting forthcoming patterns from these disadvantage dynamics which are represented by multiple life-course trajectories evolutions over time. In this paper, given longitudinal trajectories created from HILDA survey waves, we develop a model with Long Short-term Memory recurrent neural networks to generate complex trajectory sequences with long-range structure. Our method uses a multi-layered Long Short-Term Memory (LSTM) approach to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector. The generated sequences over time use the social exclusion monitor (SEM) indicator to determine the level of social disadvantage for each individual. The sequences are encoded by predefined social exclusion factors, which are binary values to indicate the occurrence of corresponding factors. To model the correlations among social exclusion domains, we use the Mixture Density Networks which are parameterized by the outputs of LSTM. Our main result is the high prediction accuracy on personal life course trajectories created from real HILDA data. Moreover, the proposed model can synthesize, and impute some missing trajectories given partial observations from respondent individuals. More importantly, we examine the relative roles of different advantage dimensions in explaining changes in life trajectories in Australia, and find that the domains of employment, education, community and personal safety are highly correlated to the decreased disadvantage measurement. While, domains regarding material resources, health and social support are of direct relevance to increase social disadvantage with varied contribution extent.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For instance, the exponential function is typically applied to outputs used as scale parameters, which are required to be positive.
References
Alkire, S., Foster, J.: Counting and multidimensional poverty measurement. J. Public Econ. 95(7–8), 476–487 (2011)
Azpitarte, F.: Has economic growth in Australia been good for the income-poor? And for the multidimensionally poor? Soc. Indic. Res. 113(1), 1–37 (2014)
Azpitarte, F.: Social exclusion monitor bulletin (2013). http://library.bsl.org.au/jspui/bitstream/1/6083/1/AzpitarteBowman_Social_exclusion_monitor_bulletin_Jun2015.pdf
Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient decent is difficult. IEEE Trans. Neural Netw. 5(2), 157–166 (1994)
Bishop, C.M.: Mixture density networks. Technical report (1994)
Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, New York (1995)
Boulanger-Lewandowski, N., Bengio, Y., Vincent, P.: Modeling temporal dependencies in high-dimensional sequences: application to polyphonic music generation and transcription. In: International Conference on Machine Learning (2012)
Bourguignon, F., Ferreira, F.H.G., Leite, P.G.: Beyond oaxaca-blinder: accounting for differences in household income distributions. J. Econ. Inequal. 6(2), 117–148 (2008)
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using rnn encoder-decoder for statistical machine translation (2014). arXiv preprint arXiv:1406.1078
Eckmann, J.P., Kamphorst, S.O., Ruelle, D.: Recurrence plots of dynamical systems. Europhys. Lett. 5(9), 973–977 (1987)
Graves, A.: Generating sequences with recurrent neural networks (2014). arXiv preprint arXiv:1308.0850v5
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Martinez Jr., A., Perales, F.: The dynamics of multidimensional poverty in contemporary australia. Soc. Indic. Res. 130(2), 479–496 (2017)
Kostenko, W., Scutella R., Wilkins, R.: Estimates of poverty and social exclusion in Australia: a multidimensional approach. In: 6th Joint Economic and Social Outlook Conference, Melbourne (2009)
Organisation of Economic Co-operation and Development.: Is work the best antidote to poverty? Chapter 3 in OECD employment outlook 2009: trackling the Jobs crisis (2009)
Rosanna, S., Roger, W.: Measuring poverty and social exclusion in Australia: a proposed multidimensional framework for identifying socio-economic disadvantage. Melbourne Institute of Applied Economic and Social Research, Australia (2009)
Rosanna, S., Roger, W., Weiping, K.: Intensity and persistence of individual’s social exclusion in australia. Aust. J. Soc. Issues 48(3), 273–298 (2013)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)
Shorrocks, A.F.: Decomposition procedures for distributed analysis: a unified framework based on the shapley value. J. Econ. Inequal. 11(1), 179–191 (2013)
Credit Suisse: Global wealth report 2014 zurich: Credit suisse group (2015). https://publications.credit-suisse.com/tasks/render/file/?fileID=60931FDE-A2D2-F568-B041B58C5EA591A
Summerfield, M., Freidin, S., Hahn, M., La, N., Li, N., Macalalad, N., O’Shea, M., Watson, N., Wilkins, R., Wooden, M.: HILDA user manual release 15. Melbourne Institute of Applied Economic and Social Research, University of Melbourne (2016)
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems (2014)
Tieleman, T., Hinton, G.: Lecture 6.5-RMSPROP: Divide the gradient by a running average of its recent magnitude. Technical report Neural networks ofr machine learning (2012)
Wang, Y., Huang, X., Lin, W.: Clustering via geometric median shift over Riemannian manifolds. Inf. Sci. 220, 292–305 (2013)
Wang, Y., Lin, X., Lin, W., Zhang, Q., Zhang, W.: Shifting multi-hypergraphs via collaborative probabilistic voting. Knowl. Inf. Syst. 46(3), 515–536 (2016)
Wang, Y., Lin, X., Lin, W., Zhang, W.: Robust landmark retrieval. In: ACM Multimedia, Effective Multi-query Expansions (2015)
Wang, Y., Lin, X., Lin, W., Zhang, W.: Effective multi-query expansions: collaborative deep networks for robust landmark retrieval. IEEE Trans. Image Proc. 26(3), 1393–1404 (2017)
Wang, Y., Lin, X., Lin, W., Zhang, W., Zhang, Q.: Towards subspace clustering for multi-modal data. In: ACM Multimedia, Exploiting Correlation Consensus (2014)
Wang, Y., Lin, X., Lin, W., Zhang, W., Zhang, Q.: Learning Bridging Mapping for Cross-modal Hashing. In: ACM SIGIR, LBMCH (2015)
Wang, Y., Lin, X., Lin, W., Zhang, W., Zhang, Q., Huang, X.: Robust subspace clustering for multi-view data by exploiting correlation consensus. IEEE Trans. Image Proc. 24(11), 3939–3949 (2015)
Wang, Y., Lin, X., Zhang, Q.: Towards metric fusion on multi-view data: a cross-view based graph random walk approach. In: ACM CIKM(2013)
Wang, Y., Zhang, W., Wu, L., Lin, X., Fang, M., Pan, S.: Iterative views agreement: an iterative low-rank based structured optimization method to multi-view spectral clustering. In: IJCAI (2016)
Wang, Y., Zhang, W., Lin, W., Lin, X., Zhao, X.: Unsupervised metric fusion over multiview data by graph random walk-based cross-view diffusion. IEEE Trans. Neural Netw. Learn. Syst. 28(1), 57–70 (2017)
Watson, N., Wooden, M. Identifying factors affecting longitudinal survey response chapter 10. Methodol. Longitud. Surv. 1, 157–182 (2009)
Whiteford, P.: Australia: Inequality and Prosperity and their Impacts in a Radical Welfare State. Crawford School of Public Polic, The Australian National University, Social Policy Action Research Centre, Mimeo (2013)
Williams, R., Zipse, D.: Gradient-based learning algorithms for recurrent networks and their computational complexity. Back Propag. Theory Archit. Appl. 1, 433–486 (1995)
Lin, W., Shen, C., van den Hengel, A.: Deep linear discriminant analysis on fisher networks: a hybrid architecture for person re-identification. Pattern Recogn. 65, 238–250 (2017)
Lin, W., Wang, Y.: Robust hashing for multi-view data: jointly learning low-rank kernelized similarity consensus and hash functions. Image Vis. Comput. 57, 58–66 (2017)
Wu, L., Wang, Y., Gao, J., Li, X.: Deep adaptive feature embedding with local sample distributions for person re-identification (2017). arXiv preprint arXiv:1706.03160
Wu, L., Wang, Y., Li, X., Gao, J.: What-and-where to match: Deep spatially multiplicative integration networks for person re-identification (2017). arXiv preprint arXiv:1707.07074
Wu, L., Wang, Y., Pan, S.: Exploiting attribute correlations: a novel trace lasso-based weakly supervised dictionary learning method. IEEE Trans. Cybern. 99, 1–12 (2016)
Wu, L., Wang, Y., Shepherd, J.: Efficient image and tag co-ranking: a bregman divergence optimization method. In: Proceedings of the 21st ACM International Conference on Multimedia. ACM (2013)
Acknowledgement
Lin Wu’s research was funded by the Australian Research Council Centre of Excellence in Children and Families over the Life Course and supported by a Life Course Centre Staff Exchange Scheme 2017. We acknowledge the use of HILDA survey funded by Australian Government Department of Social Services and support from The Melbourne Institute.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Wu, L., Haynes, M., Smith, A., Chen, T., Li, X. (2017). Generating Life Course Trajectory Sequences with Recurrent Neural Networks and Application to Early Detection of Social Disadvantage. In: Cong, G., Peng, WC., Zhang, W., Li, C., Sun, A. (eds) Advanced Data Mining and Applications. ADMA 2017. Lecture Notes in Computer Science(), vol 10604. Springer, Cham. https://doi.org/10.1007/978-3-319-69179-4_16
Download citation
DOI: https://doi.org/10.1007/978-3-319-69179-4_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-69178-7
Online ISBN: 978-3-319-69179-4
eBook Packages: Computer ScienceComputer Science (R0)