Identifying and predicting social lifestyles in people’s trajectories by neural networks

Eyal Ben Zion, Boaz Lerner

Research output: Contribution to journalArticlepeer-review

8 Scopus citations

Abstract

In this research, we exploit repeated parts in daily trajectories in people’s movements, which we refer to as mobility patterns, to train models to identify and predict a person’s lifestyles. We use cellular data of a group (“society”) of people and represent a person’s daily trajectory using semantic labels (e.g., “home”, “work”, and “gym”) given to the main places of interest (POI) he has visited during the day, as determined collectively based on interviewing all people of the group. First, in an unsupervised manner using a neural network (NN), we embed POI-based daily trajectories that always appear together with others in consecutive weeks and identify the result of this embedding with social lifestyles. Second, using these lifestyles as labels for lifestyle prediction, user POI-based daily trajectories are used to train a convolutional NN to extract mobility patterns in the trajectories and a dynamic NN with flexible memory to assemble these patterns to predict a lifestyle for a trajectory never-seen-before. The two-stage algorithm shows model accuracy and generalizability in lifestyle identification and prediction (both for a novel trajectory and a novel user) that are superior to those shown by state-of-the-art algorithms. The code for the algorithm and data sets used in our experiments are available online.

Original languageEnglish
Article number45
JournalEPJ Data Science
Volume7
Issue number1
DOIs
StatePublished - 1 Dec 2018

Keywords

  • Convolutional neural network
  • Embedding
  • Human behavior
  • Lifestyle
  • Long short-term memory
  • Mobility patterns
  • Place of interest
  • Recurrent neural network
  • Sequence classification
  • Word2vec

Fingerprint

Dive into the research topics of 'Identifying and predicting social lifestyles in people’s trajectories by neural networks'. Together they form a unique fingerprint.

Cite this