Generating life course trajectory sequences with recurrent neural networks and application to early detection of social disadvantage

Conference item


Wu, Lin, Haynes, Michele A., Smith, Andrew, Chen, Tong and Li, Xue. (2017). Generating life course trajectory sequences with recurrent neural networks and application to early detection of social disadvantage. In G. Cong, W. P. Wei and E. Zhang, C. Li and A. Sun (Ed.). Singapore: Springer Nature. pp. 225 - 242 https://doi.org/10.1007/978-3-319-69179-4
AuthorsWu, Lin, Haynes, Michele A., Smith, Andrew, Chen, Tong and Li, Xue
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.

Year2017
JournalAdvanced Data Mining and Applications,13th International Conference, ADMA 2017 Singapore, November 5-6, 2017 Proceedings
PublisherSpringer Nature
Digital Object Identifier (DOI)https://doi.org/10.1007/978-3-319-69179-4
Publisher's version
File Access Level
Controlled
Page range225 - 242
Research GroupInstitute for Learning Sciences and Teacher Education (ILSTE)
Place of publicationSingapore
EditorsG. Cong, W. P. Wei and E. Zhang, C. Li and A. Sun
Permalink -

https://acuresearchbank.acu.edu.au/item/85yvv/generating-life-course-trajectory-sequences-with-recurrent-neural-networks-and-application-to-early-detection-of-social-disadvantage

Restricted files

Publisher's version

  • 90
    total views
  • 0
    total downloads
  • 3
    views this month
  • 0
    downloads this month
These values are for the period from 19th October 2020, when this repository was created.

Export as

Related outputs

Innovation in methodology : Longitudinal analysis of progression in teacher preparation
Haynes, Michele and Smith, Andrew. (2021). Innovation in methodology : Longitudinal analysis of progression in teacher preparation. In In Wyatt-Smith, Claire, Adie, Lenore and Nuttall, Joce (Ed.). Teaching performance assessments as a cultural disruptor in initial teacher education : Standards, evidence and collaboration pp. 201-215 Springer Nature. https://doi.org/10.1007/978-981-16-3705-6_16
Long-term outcomes after bariatric surgery: A systematic review and meta-analysis of weight loss at 10 or more years for all bariatric procedures and a single-centre review of 20-year outcomes after adjustable gastric banding
O'Brien, Paul E., Hindle, Annemarie, Brennan, Leah, Skinner, Stewart, Burton, Paul, Smith, Andrew, Crosthwaite, Gary and Brown, Wendy A.. (2019). Long-term outcomes after bariatric surgery: A systematic review and meta-analysis of weight loss at 10 or more years for all bariatric procedures and a single-centre review of 20-year outcomes after adjustable gastric banding. Obesity Surgery. 29(1), pp. 3 - 14. https://doi.org/10.1007/s11695-018-3525-0
The effect of weight loss on Indigenous Australians with diabetes: A study of feasibility, acceptability and effectiveness of laparoscopic adjustable gastric banding
O'Brien, Paul E., DeWitt, Dawn E., Laurie, Cheryl E., Brennan, Leah, Wentworth, John M., Anderson, Margaret, O'Dea, Kerin, Dean, Felicia, Smith, Andrew and Dalton, David P.. (2016). The effect of weight loss on Indigenous Australians with diabetes: A study of feasibility, acceptability and effectiveness of laparoscopic adjustable gastric banding. Obesity Surgery. 26(1), pp. 45 - 53. https://doi.org/10.1007/s11695-015-1733-4
Visualising conversations between care home staff and residents with dementia
Baker, Rosemary, Angus, Daniel, Conway, Erin Renee, Baker, Katharine S., Gallois, Cindy, Smith, Andrew, Wiles, Janet and Chenery, Helen J.. (2015). Visualising conversations between care home staff and residents with dementia. Ageing and Society. 35(2), pp. 270 - 297. https://doi.org/10.1017/S0144686X13000640
A trial of family partnership and education interventions in heart failure
Dunbar, S, Clark, P, Reilly, C, Gary, R, Smith, Andrew, McCarty, F, Higgins, Melinda, Grossniklaus, D, Kaslow, N and Frediani, J. (2013). A trial of family partnership and education interventions in heart failure. Journal of Cardiac Failure. https://doi.org/10.1016/j.cardfail.2013.10.007