Profiling presence patterns and segmenting user locations from cell phone data

TL;DR

This paper introduces a novel, scalable method to accurately infer commuting origins and destinations from cell phone data by analyzing individual spatial-temporal patterns using unsupervised machine learning, significantly outperforming existing heuristic approaches.

Contribution

The authors develop a new approach that leverages Eigen-decomposition and probability distributions of geo-temporal data to improve location labeling accuracy without heavy computational costs.

Findings

Home and work locations identified with 79% and 34% higher accuracy.

Method outperforms heuristic rules in existing literature.

Approach is scalable and adaptable to various datasets.

Abstract

The dynamic monitoring of commuting flows is crucial for improving transit systems in fast-developing cities around the world. However, existing methodology to infer commuting originations and destinations have to either rely on large-scale survey data, which is inherently expensive to implement, or on Call Detail Records but based on ad-hoc heuristic assignment rules based on the frequency of appearance at given locations. In this paper, we proposed a novel method to accurately infer the point of origin and destinations of commuting flows based on individual's spatial-temporal patterns inferred from Call Detail Records. Our project significantly improves the accuracy upon the heuristic assignment rules popularly adopted in the literature. Starting with the historical data of geo-temporal travel patterns for a panel of individuals, we create, for each person-location, a vector of probability distribution capturing the likelihood that the person will appear in that location for a given the time of day. Stacked in this way, the matrix of historical geo-temporal data enables us to apply Eigen-decomposition and use unsupervised machine learning techniques to extract commonalities across locations for the different groups of travelers, which ultimately allows us to make inferences and create labels, such as home and work, on specific locations. Testing the methodology on real-world data with known location labels shows that our method identifies home and workplaces with significant accuracy, improving upon the most commonly used methods in the literature by 79% and 34%, respectively. Most importantly, our methodology does not bear any significant computation burden and is easily scalable and easily expanded to other real-world data with historical tracking.