Using Deep Learning to Predict Demographics from Mobile Phone Metadata

Bjarke Felbo, Pål Sundsøy, Alex 'Sandy' Pentland, Sune Lehmann, Yves-Alexandre de Montjoye

Feb 13, 2016 (modified: Feb 13, 2016) ICLR 2016 workshop submission readers: everyone
  • CMT id: 296
  • Abstract: Mobile phone metadata are increasingly used to study human behavior at large-scale. There has recently been a growing interest in predicting demographic information from metadata. Previous approaches relied on hand-engineered features. We here apply, for the first time, deep learning methods to mobile phone metadata using a convolutional network. Our method provides high accuracy on both age and gender prediction. These results show great potential for deep learning approaches for prediction tasks using standard mobile phone metadata.
  • Conflicts: mit.edu, dtu.dk, harvard.edu, ku.dk, telenor.com, telenor.no

Loading