Affordable Access

Access to the full text

Evaluation of home detection algorithms on mobile phone data using individual-level ground truth

Authors
  • Pappalardo, Luca1
  • Ferres, Leo2, 3, 4
  • Sacasa, Manuel3
  • Cattuto, Ciro5, 4
  • Bravo, Loreto2, 3
  • 1 National Research Council (CNR), Pisa, Italy , Pisa (Italy)
  • 2 Universidad del Desarrollo, Santiago, Chile , Santiago (Chile)
  • 3 Telefónica R&D, Santiago, Chile , Santiago (Chile)
  • 4 ISI Foundation, Turin, Italy , Turin (Italy)
  • 5 University of Turin, Turin, Italy , Turin (Italy)
Type
Published Article
Journal
EPJ Data Science
Publisher
Springer Berlin Heidelberg
Publication Date
Jun 02, 2021
Volume
10
Issue
1
Identifiers
DOI: 10.1140/epjds/s13688-021-00284-9
Source
Springer Nature
Keywords
License
Green

Abstract

Inferring mobile phone users’ home location, i.e., assigning a location in space to a user based on data generated by the mobile phone network, is a central task in leveraging mobile phone data to study social and urban phenomena. Despite its widespread use, home detection relies on assumptions that are difficult to check without ground truth, i.e., where the individual who owns the device resides. In this paper, we present a dataset that comprises the mobile phone activity of sixty-five participants for whom the geographical coordinates of their residence location are known. The mobile phone activity refers to Call Detail Records (CDRs), eXtended Detail Records (XDRs), and Control Plane Records (CPRs), which vary in their temporal granularity and differ in the data generation mechanism. We provide an unprecedented evaluation of the accuracy of home detection algorithms and quantify the amount of data needed for each stream to carry out successful home detection for each stream. Our work is useful for researchers and practitioners to minimize data requests and maximize the accuracy of the home antenna location.

Report this publication

Statistics

Seen <100 times