Understanding human mobility patterns is a significant research endeavor that has recently received considerable attention. Developing the science to describe and predict how people move from one place to another during their daily lives promises to address a wide range of societal challenges: from predicting the spread of infectious diseases, improving urban planning, to devising effective emergency response strategies. This presentation will discuss a Bayesian framework to analyse an individual’s mobility patterns and identify departures from routine. It is able to detect both spatial and temporal departures from routine based on heterogeneous sensor data (GPS, Cell Tower, social media, ..) and outperforms existing state-of-the-art predictors. Applications include mobile digital assistants (e.g., Google Now), mobile advertising (e.g., LivingSocial), and crowdsourcing physical tasks (e.g., TaskRabbit).
3. Human Mobility - Credits
University of Southampton
BAE Systems ATC
James McInerney
Sebastian Stein
Alex Rogers
Nick Jennings
Dave Nicholson
Reference:
J. McInerney, S. Stein, A. Rogers, and N. R. Jennings (2013).
Breaking the habit: measuring and predicting departures from
routine in individual human mobility. Pervasive and Mobile
Computing, 9, (6), 808-822.
Submitted KDD paper
10. Human Mobility
Human mobility is highly predictable
Average predictability in the next hour is 93% [Song 2010]
Distance little or no impact
High degree of spatial and temporal regularity
Spatial: centered around a small number of base locations
Temporal: e.g., workweek / weekend
“…we find a 93% potential predictability in user mobility
across the whole user base. Despite the significant
differences in the travel patterns, we find a remarkable
lack of variability in predictability, which is largely
independent of the distance users cover on a regular
basis.”
13. Breaking the Habit
However, regular patterns not the full story
travelling to another city on a weekend break or while on
sick leave
Breaks in regular patterns signal potentially
interesting events
Being in an unfamiliar place at an unfamiliar time
requires extra context aware assistance
E.g., higher demand for map & recommendation apps,
mobile advertising more relevant, …
Predict future departures from routine?
14. Applications
Optimize public transport
Insight into social behaviour
Spread of disease
(Predictive) Recommender systems
Based on user habits (e.g., Google Now, Sherpa)
Context aware advertising
Crime investigation
Urban planning
…
Obvious privacy & de-anonymization concerns
-> Eric Drass’ talk
16. Modeling Mobility
Entropy measures typically used to determine regularity in
fixed time slots
Well understood measures, wide applicability
Break down when considering prediction or higher level structure
Model based
Can consider different types of structure in mobility (i.e., sequential
and temporal)
Can deal with heterogeneous data sources
Allows incorporation of domain knowledge (e.g., calendar
information)
Can build extensions that deal with trust
Allows for prediction
Bayesian approach
distribution over locations
enables use as a generative model
20. Probabilistic Models
Model can be run forwards or backwards
Forwards (generation): parameters -> data
E.g., use a distribution
over word pair
frequencies to
generate sentences
22. Building the model
We want to model departures from routine
Assume assignment of a person to a hidden location
at all time steps (even when not observed)
Discrete latent locations
Correspond to “points of interest”
e.g., home, work, gym, train station, friend's house
23. Latent Locations
Augment with temporal structure
Temporal and periodic assumption to behaviour
e.g., tend to be home each night at 1am
e.g., often in shopping district on Sat afternoon
24. Add Sequential Structure
Added first-order Markov dynamics
e.g., usually go home after work
can extend to more complex sequential structures
25. Add Departure from Routine
zn = 0 : routine
zn = 1 : departure from routine
31. Inference is Challenging
Exact inference intractable
Can perform approximate inference using:
Expectation maximisation algorithm
Gibbs sampling, or other Markov chain Monte Carlo
Fast
But point estimates of parameters
Full distributions (converges to exact)
But slow
Variational approximation
Full distributions based on induced factorisation of model
And fast
32. Variational Approximation
Advantages
Straightforward parallelisation by user
Months of mobility data ~ hours
Updating previous day's parameters ~ minutes
Variational approximation amenable to fully online
inference
M. Hoffman, D. Blei, C. Wang, and J. Paisley.
Stochastic variational inference. arXiv:1206.7051,
2012
45. Conclusion & Future Work
Summary
Novel model for learning and predicting departures from routine
Limitations
Need better ground truth for validation
Finding ways to make the model explain why each departure
from routine happened.
Needs more data (e.g., from people who know each other, using
weather data, app usage data, …).
Future Work
Incorporating more advanced sequential structure into the model
e.g., hidden semi-Markov model, sequence memoizer
Supervised learning of what “interesting" mobility looks like
More data sources
Online inference
Taxi drivers