Using Deep Learning to Predict Demographics from Mobile Phone Metadata

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.