{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/modeling-the-temporal-nature-of-human","title":"Modeling the Temporal Nature of Human Behavior for Demographics Prediction","arxiv_id":"1511.06660","date":"2015-11-20","proceeding":null,"authors":["Bjarke Felbo","Pål Sundsøy","Alex 'Sandy' Pentland","Sune Lehmann","Yves-Alexandre de Montjoye"],"abstract":"Mobile phone metadata is increasingly used for humanitarian purposes in\ndeveloping countries as traditional data is scarce. Basic demographic\ninformation is however often absent from mobile phone datasets, limiting the\noperational impact of the datasets. For these reasons, there has been a growing\ninterest in predicting demographic information from mobile phone metadata.\nPrevious work focused on creating increasingly advanced features to be modeled\nwith standard machine learning algorithms. We here instead model the raw mobile\nphone metadata directly using deep learning, exploiting the temporal nature of\nthe patterns in the data. From high-level assumptions we design a data\nrepresentation and convolutional network architecture for modeling patterns\nwithin a week. We then examine three strategies for aggregating patterns across\nweeks and show that our method reaches state-of-the-art accuracy on both age\nand gender prediction using only the temporal modality in mobile metadata. We\nfinally validate our method on low activity users and evaluate the modeling\nassumptions.","url_abs":"http://arxiv.org/abs/1511.06660v5","url_pdf":"http://arxiv.org/pdf/1511.06660v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"modeling-the-temporal-nature-of-human","repo_url":"https://github.com/yvesalexandre/convnet-metadata","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"gender-prediction","task_name":"Gender Prediction"},{"task_slug":"humanitarian","task_name":"Humanitarian"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}