A refined limit on the predictability of human mobility

Smith, Gavin; Wieser, Romain; Goulding, James; Barrack, Duncan

doi:10.1109/percom.2014.6813948

Cited by 61 publications

(78 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This framework has been further explored to refine the estimate of the upper limit. Specifically, Lin et al [16] study the effects of spatial and temporal resolution on the predictability limit, Smith et al [17] consider spatial reachability constraints when selecting the next place to visit, and obtain a tighter upper bound of 81-85%, and Lu et al [4] analyze the predictability of the population of Haiti after the earthquake in 2010, and find an upper limit of predictability of around 85%. The work described above focuses on estimating an upper limit of predictability for an individual based on an estimate of the entropy their trajectory.…”

Section: Related Workmentioning

confidence: 99%

Understanding predictability and exploration in human mobility

2018

View full text Add to dashboard Cite

Predictive models for human mobility have important applications in many fields including traffic control, ubiquitous computing, and contextual advertisement. The predictive performance of models in literature varies quite broadly, from over 90% to under 40%. In this work we study which underlying factors -in terms of modeling approaches and spatio-temporal characteristics of the data sources -have resulted in this remarkably broad span of performance reported in the literature. Specifically we investigate which factors influence the accuracy of next-place prediction, using a high-precision location dataset of more than 400 users observed for periods between 3 months and one year. We show that it is much easier to achieve high accuracy when predicting the time-bin location than when predicting the next place. Moreover, we demonstrate how the temporal and spatial resolution of the data have strong influence on the accuracy of prediction. Finally we reveal that the exploration of new locations is an important factor in human mobility, and we measure that on average 20-25% of transitions are to new places, and approx. 70% of locations are visited only once. We discuss how these mechanisms are important factors limiting our ability to predict human mobility.

show abstract

Section: Related Workmentioning

confidence: 99%

Understanding predictability and exploration in human mobility

2018

View full text Add to dashboard Cite

show abstract

“…Therefore, the "resolution" of our square based home detection is around 70 meters ( √ 2 * 100/2 ≈ 70 meters). Similar to the previous work [1], [10], [11], we only focus on those "active users" who have sent at least 5 tweets. Also following these studies, we use user's hourly traces (only take one location for each hour in our sampling duration) instead of taking account of every single check-in.…”

Section: A Data Set and Pre-processingmentioning

confidence: 99%

“…We evaluate our method on two large Twitter data sets from the Great New York City(NYC) Area and the Bay Area and the results show that our method is capable of locating homes within a 100 by 100 meter square with a 70% accuracy and applicable to 71% and 76% active Twitter users in NYC and the Bay Area, respectively. An active Twitter users is defined as one who sent at least 5 geo-tagged tweets under using the same definition as in [1], [10], [11]. Utilizing the rich text content within tweets, we explore the health conditions of people in different zip code districts.…”

mentioning

confidence: 99%

Home Location Inference from Sparse and Noisy Data: Models and Applications

Luo

Kautz

et al. 2015

2015 IEEE International Conference on Data Mining Workshop (ICDMW)

View full text Add to dashboard Cite

Accurate home location is increasingly important for urban computing. Existing methods either rely on continuous (and expensive) GPS data or suffer from poor accuracy. In particular, the sparse and noisy nature of social media data poses serious challenges in pinspointing where people live at scale. We revisit this research topic and infer home location within 100 by 100 meter squares at 70% accuracy for 71% and 76% of active users in New York City and the Bay Area, respectively. We believe this is the first time home location is detected at such a fine granularity using sparse and noisy data. Since people spend a large portion of their time at home, our model enables novel applications that were previously impossible. As a specific example, we focus on modeling people's health at scale.Home, as one of the most important locations in people's mobility patterns, is the key to understanding many aspects of urban life and environments. With the knowledge of where people actually live, researchers are able to model the distribution of population, study human mobility patterns, infer life styles, and even discover the correlation between home location and other important aspects such as health conditions, disease diffusion and environment changes.Much of the research in above mentioned areas is based on surveys and census, which are costly and often incur a delay that hamper real-time analysis and response. Fortunately, the wide adoption of geotagged social media provides us a new opportunity to feel the pulse of cities. In this paper, we present a machine learning based approach to detecting home locations at the population level only based on geo-tagged tweets and use the estimated home locations to investigate these crucial aspects of urban life.

show abstract

“…A number of studies [7,8] have established that the second-order Markov model (2-MM) has the best accuracies, up to 95%, for predicting human mobility, and that higher-order MM (>2) is not necessarily more accurate, but is often less precise. However, the 2-MM always utilizes historical geo-spatial trajectories to train a transition probability matrix and in 2-MM (see Figure 3a) the probability of each destination is computed based only on the present and immediate past grids of interest that a user visited without using temporal information.…”

Section: Second-order Markov Model For Trajectory Predictionmentioning

confidence: 99%

“…TraPlan contains three essential techniques: (1) constrained network R-tree (CNR-tree), which is a two-tiered dynamic index structure of moving objects based on transportation networks; (2) a region-of-interest (RoI) discovery algorithm, which is employed to partition a large number of trajectory points into distinct clusters; and (3) a Trajectory-Prediction (TP) approach based on frequent trajectory patterns (FTP) tree, called FTP-mining, which is proposed to discover FTPs to infer future locations of objects within RoIs. The Markov chain (MC) model has been adopted by a number of works on predicting human mobility [7,8] to incorporate some amount of memory. Second-order MC has the best accuracies, up to 95%, for predicting human mobility, and higher order MC (>2) is not necessarily more accurate, but is often less precise.…”

Section: Introductionmentioning

confidence: 99%

Sparse Trajectory Prediction Based on Multiple Entropy Measures

Zhang

Liu

Xia

et al. 2016

Entropy

View full text Add to dashboard Cite

Trajectory prediction is an important problem that has a large number of applications. A common approach to trajectory prediction is based on historical trajectories. However, existing techniques suffer from the "data sparsity problem". The available historical trajectories are far from enough to cover all possible query trajectories. We propose the sparsity trajectory prediction algorithm based on multiple entropy measures (STP-ME) to address the data sparsity problem. Firstly, the moving region is iteratively divided into a two-dimensional plane grid graph, and each trajectory is represented as a grid sequence with temporal information. Secondly, trajectory entropy is used to evaluate trajectory's regularity, the L-Z entropy estimator is implemented to calculate trajectory entropy, and a new trajectory space is generated through trajectory synthesis. We define location entropy and time entropy to measure the popularity of locations and timeslots respectively. Finally, a second-order Markov model that contains a temporal dimension is adopted to perform sparse trajectory prediction. The experiments show that when trip completed percentage increases towards 90%, the coverage of the baseline algorithm decreases to almost 25%, while the STP-ME algorithm successfully copes with it as expected with only an unnoticeable drop in coverage, and can constantly answer almost 100% of query trajectories. It is found that the STP-ME algorithm improves the prediction accuracy generally by as much as 8%, 3%, and 4%, compared to the baseline algorithm, the second-order Markov model (2-MM), and sub-trajectory synthesis (SubSyn) algorithm, respectively. At the same time, the prediction time of STP-ME algorithm is negligible (10 µs), greatly outperforming the baseline algorithm (100 ms).

show abstract

A refined limit on the predictability of human mobility

Cited by 61 publications

References 18 publications

Understanding predictability and exploration in human mobility

Understanding predictability and exploration in human mobility

Home Location Inference from Sparse and Noisy Data: Models and Applications

Sparse Trajectory Prediction Based on Multiple Entropy Measures

Contact Info

Product

Resources

About