Identifying Hidden Visits from Sparse Call Detail Record Data

TL;DR

This paper introduces a data fusion method to detect hidden visits in sparse call detail record data, significantly improving mobility inference accuracy using machine learning models on a large real-world dataset.

Contribution

It presents a novel data fusion approach combining granular cellular data and communication records to identify hidden visits, addressing a key limitation in CDR-based mobility analysis.

Findings

Over 10% of displacements involve hidden visits.

Significant improvement over naive no-hidden-visit rule.

Effective use of machine learning models for inference.

Abstract

Despite a large body of literature on trip inference using call detail record (CDR) data, a fundamental understanding of their limitations is lacking. In particular, because of the sparse nature of CDR data, users may travel to a location without being revealed in the data, which we refer to as a "hidden visit". The existence of hidden visits hinders our ability to extract reliable information about human mobility and travel behavior from CDR data. In this study, we propose a data fusion approach to obtain labeled data for statistical inference of hidden visits. In the absence of complementary data, this can be accomplished by extracting labeled observations from more granular cellular data access records, and extracting features from voice call and text messaging records. The proposed approach is demonstrated using a real-world CDR dataset of 3 million users from a large Chinese city. Logistic regression, support vector machine, random forest, and gradient boosting are used to infer whether a hidden visit exists during a displacement observed from CDR data. The test results show significant improvement over the naive no-hidden-visit rule, which is an implicit assumption adopted by most existing studies. Based on the proposed model, we estimate that over 10% of the displacements extracted from CDR data involve hidden visits. The proposed data fusion method offers a systematic statistical approach to inferring individual mobility patterns based on telecommunication records.