Beware Thy Bias: Scaling Mobile Phone Data to Measure Traffic Intensities

Abstract

Mobile phone data are a novel data source to generate mobility information from Call Detail Records (CDRs). Although mobile phone data can provide us with valuable insights in human mobility, they often show a biased picture of the traveling population. This research, therefore, focuses on correcting for these biases and suggests a new method to scale mobile phone data to the true traveling population. Moreover, the scaled mobile phone data will be compared to roadside measurements at 100 different locations on Dutch highways. We infer vehicle trips from the mobile phone data and compare the scaled counts with roadside measurements. The results are evaluated for October 2015. The proposed scaling method shows very promising results with near identical vehicle counts from both data sources in terms of monthly, weekly, and hourly vehicle counts. This indicates the scaling method, in combination with mobile phone data, is able to correctly measure traffic intensities on highways, and thereby able to anticipate calibrated human mobility behaviour. Nevertheless, there are still some discrepancies—for one, during weekends—calling for more research. This paper serves researchers in the field of mobile phone data by providing a proven method to scale the sample to the population, a crucial step in creating unbiased mobility information.

Artificial Intelligence (AI) and Sustainable Development Goals (SDGs): Exploring the Impact of AI on Politics and Society

“…While this paper focuses specifically on the challenge of verifying the integrity of academic certificates, the findings can easily be applied in a number of different contexts. The Special Issue closes with a contribution by Meppelink et al [16], who propose a method of using mobile phone data to obtain reliable information on traffic, etc. To sum up, the discussion on AI and its value for our societies has only just begun.…”

Towards efficient urban road transport using multimodal traffic management

“…The input data may suffer from quality issues, including biases and inaccuracies, which affect the validity of the models and the predictions. Data bias refers to the potential inaccurate representation of the population in the dataset, which could lead to misleading conclusions if not corrected for (Richterich, 2018;Meppelink et al, 2020). In addition, large-scale mobility data can lead to privacy and ethical issues.…”

Impact of 2020 COVID-19 lockdowns on particulate air pollution across Europe

“…Biases in traffic intensity estimates derived from mobility data have been reported in business as usual conditions (Meppelink et al, 2020). However, data relative to the lockdown period in the USA have highlighted a clear 200 covariation between Apple® mobility data and gasoline demand (Ou et al, 2020), which is in turn a robust indicator for the cumulative distance covered by cars.…”