Modeling the Temporal Nature of Human Behavior for Demographics Prediction

TL;DR

This paper introduces a deep learning approach that models the temporal patterns in mobile phone metadata to predict demographic information like age and gender, achieving state-of-the-art accuracy without relying on handcrafted features.

Contribution

It proposes a novel convolutional neural network architecture that directly models raw temporal mobile data for demographic prediction, outperforming previous feature-based methods.

Findings

Achieves state-of-the-art accuracy in age and gender prediction

Effective modeling of weekly temporal patterns in mobile data

Validates approach on low activity users

Abstract

Mobile phone metadata is increasingly used for humanitarian purposes in developing countries as traditional data is scarce. Basic demographic information is however often absent from mobile phone datasets, limiting the operational impact of the datasets. For these reasons, there has been a growing interest in predicting demographic information from mobile phone metadata. Previous work focused on creating increasingly advanced features to be modeled with standard machine learning algorithms. We here instead model the raw mobile phone metadata directly using deep learning, exploiting the temporal nature of the patterns in the data. From high-level assumptions we design a data representation and convolutional network architecture for modeling patterns within a week. We then examine three strategies for aggregating patterns across weeks and show that our method reaches state-of-the-art accuracy on both age and gender prediction using only the temporal modality in mobile metadata. We finally validate our method on low activity users and evaluate the modeling assumptions.