SlideShare a Scribd company logo
1 of 46
Measuring and Predicting
Departures from Routine
in Human Mobility
Dirk Gorissen | @elazungu
PyData London - 23 February 2014
Me?
www.rse.ac.uk
Human Mobility - Credits
 University of Southampton
 James McInerney
 Sebastian Stein
 Alex Rogers
 Nick Jennings
 BAE Systems ATC
 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
 Beijing Taxi rides
 Nicholas Jing Yuan (Microsoft Research)
Human Mobility
 London in Motion - Jay Gordon (MIT)
Human Mobility: Inference
 Functional Regions of a city
 Nicholas Jing Yuan (Microsoft Research)
Human Mobility: Inference
 Jay Gordon (MIT)
Human Mobility: Inference
 Cross cuts many fields: sociology, physics, network
theory, computer science, epidemiology, …
© PNAS
© MIT
Project InMind
 Project InMind announced on 12 Feb
 $10m Yahoo-CMU collaboration on predicting human needs and
intentions
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.”
Temporal Regularity
 [Herder 2012] [Song 2010]
Spatial Regularity
 [Herder 2012] [Song 2010]
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?
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
Human Mobility: Inference
 London riots “commute”
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
Bayes Theorem
Bayesian Networks
 Bottom up: Grass is wet, what is the most likely cause?
 Top down: Its cloudy, what is the probability the grass is wet?
Hidden Markov Model
 Simple Dynamic Bayesian Network
 Shaded nodes are observed
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
Probabilistic Models
 Model can be run backwards
 Backwards (Inference): data -> parameters
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
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
Add Sequential Structure
 Added first-order Markov dynamics
 e.g., usually go home after work
 can extend to more complex sequential structures
Add Departure from Routine
 zn = 0 : routine
 zn = 1 : departure from routine
Sensors
 Noisy sensors, e.g., cell tower observations
 observed: latitude/longitude
 inferred: variance (of locations)
Reported Variance
 E.g., GPS
 observed: latitude/longitude, variance
Trustworthiness
 E.g., Eyewitness
 observed: latitude/longitude, reported variance
 inferred: trustworthiness of observation
 single latent trust value(per time step & source)
Full Model
Inference
Inference is Challenging
 Exact inference intractable
 Can perform approximate inference using:
 Expectation maximisation algorithm
 Fast
 But point estimates of parameters
 Gibbs sampling, or other Markov chain Monte Carlo
 Full distributions (converges to exact)
 But slow
 Variational approximation
 Full distributions based on induced factorisation of model
 And fast
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
Model enables
 Inference
 location
 departures from routine
 noise characteristics of observations
 trust characteristics of sensors
 Exploration/summarisation
 parameters have intuitive interpretations
 Prediction
 Future mobility (given time context)
 Future departures from routine
Performance
 Nokia Dataset (GPS only) [McInerney 2012]
Performance
Performance
 Synthetic dataset with heterogeneous, untrustworthy
observations.
 Parameters of generating model learned from OpenPaths
dataset
Performance
Implementation
 Backend inference and data processing code all python
 numpy
 scipy
 matplotlib
 UI to explore model predictions & sanity check
 flask
 d3.js
 leaflet.js
 kockout.js
 Future
 Gensim, pymc, bayespy, …
 Probabilistic programming
Map View: Observed
Map View: Inferred
Departures from Routine: Temporal
Departures from Routine: Spatial
Departures from Routine: Combined
Departures from Routine
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
Questions?
 Thank you.
 dirk.gorissen@baesystems.com | @elazungu
 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.

More Related Content

Similar to Measuring and Predicting Departures from Routine in Human Mobility by Dirk Gorissen

Effects of mobility models and nodes distribution on wireless sensors networks
Effects of mobility models and nodes distribution on wireless sensors networksEffects of mobility models and nodes distribution on wireless sensors networks
Effects of mobility models and nodes distribution on wireless sensors networksijasuc
 
A real time filtering method of positioning data with moving window mechanism
A real time filtering method of positioning data with moving window mechanismA real time filtering method of positioning data with moving window mechanism
A real time filtering method of positioning data with moving window mechanismAlexander Decker
 
hsd-faculty-lunch-jan06
hsd-faculty-lunch-jan06hsd-faculty-lunch-jan06
hsd-faculty-lunch-jan06webuploader
 
DOTI North - Data and Design; Prof Matthew Chalmers
DOTI North - Data and Design; Prof Matthew ChalmersDOTI North - Data and Design; Prof Matthew Chalmers
DOTI North - Data and Design; Prof Matthew ChalmersSnook
 
Steven Strachan - Dynamics and Interaction
Steven Strachan - Dynamics and InteractionSteven Strachan - Dynamics and Interaction
Steven Strachan - Dynamics and InteractionAIC_UCD
 
Conference talk: Understanding Vulnerabilities of Location Privacy Mechanisms...
Conference talk: Understanding Vulnerabilities of Location Privacy Mechanisms...Conference talk: Understanding Vulnerabilities of Location Privacy Mechanisms...
Conference talk: Understanding Vulnerabilities of Location Privacy Mechanisms...Zohaib Riaz
 
Mobile gaming 2009 an abstract location model
Mobile gaming 2009   an abstract location modelMobile gaming 2009   an abstract location model
Mobile gaming 2009 an abstract location modelLeif Oppermann
 
understanding the planet using satellites and deep learning
understanding the planet using satellites and deep learningunderstanding the planet using satellites and deep learning
understanding the planet using satellites and deep learningAlbert Pujol Torras
 
Modeling Crowds in Urban Spaces
Modeling Crowds in Urban SpacesModeling Crowds in Urban Spaces
Modeling Crowds in Urban SpacesJavier Espinosa
 
90seconds Presentation
90seconds Presentation90seconds Presentation
90seconds Presentationpbihler
 
Integrated Hidden Markov Model and Kalman Filter for Online Object Tracking
Integrated Hidden Markov Model and Kalman Filter for Online Object TrackingIntegrated Hidden Markov Model and Kalman Filter for Online Object Tracking
Integrated Hidden Markov Model and Kalman Filter for Online Object Trackingijsrd.com
 
Embedded Sensing and Computational Behaviour Science
Embedded Sensing and Computational Behaviour ScienceEmbedded Sensing and Computational Behaviour Science
Embedded Sensing and Computational Behaviour ScienceDaniel Roggen
 
Contextual Dissonance: Design Bias in Sensor-Based Experience Sampling Methods
Contextual Dissonance: Design Bias in Sensor-Based Experience Sampling MethodsContextual Dissonance: Design Bias in Sensor-Based Experience Sampling Methods
Contextual Dissonance: Design Bias in Sensor-Based Experience Sampling MethodsNeal Lathia
 
Transforming instagram data into location intelligence
Transforming instagram data into location intelligenceTransforming instagram data into location intelligence
Transforming instagram data into location intelligencesuresh sood
 
Semantic Sensor Networks and Linked Stream Data
Semantic Sensor Networks and Linked Stream DataSemantic Sensor Networks and Linked Stream Data
Semantic Sensor Networks and Linked Stream DataOscar Corcho
 
Human activity recognition updated 1 - Copy.pptx
Human activity recognition updated 1 - Copy.pptxHuman activity recognition updated 1 - Copy.pptx
Human activity recognition updated 1 - Copy.pptxBhaveshKhuje
 
Enhancing indoor localization using IoT techniques
Enhancing indoor localization using IoT techniquesEnhancing indoor localization using IoT techniques
Enhancing indoor localization using IoT techniquesMohamed Nabil, MSc.
 

Similar to Measuring and Predicting Departures from Routine in Human Mobility by Dirk Gorissen (20)

Effects of mobility models and nodes distribution on wireless sensors networks
Effects of mobility models and nodes distribution on wireless sensors networksEffects of mobility models and nodes distribution on wireless sensors networks
Effects of mobility models and nodes distribution on wireless sensors networks
 
A real time filtering method of positioning data with moving window mechanism
A real time filtering method of positioning data with moving window mechanismA real time filtering method of positioning data with moving window mechanism
A real time filtering method of positioning data with moving window mechanism
 
hsd-faculty-lunch-jan06
hsd-faculty-lunch-jan06hsd-faculty-lunch-jan06
hsd-faculty-lunch-jan06
 
www.ijerd.com
www.ijerd.comwww.ijerd.com
www.ijerd.com
 
DOTI North - Data and Design; Prof Matthew Chalmers
DOTI North - Data and Design; Prof Matthew ChalmersDOTI North - Data and Design; Prof Matthew Chalmers
DOTI North - Data and Design; Prof Matthew Chalmers
 
Steven Strachan - Dynamics and Interaction
Steven Strachan - Dynamics and InteractionSteven Strachan - Dynamics and Interaction
Steven Strachan - Dynamics and Interaction
 
Conference talk: Understanding Vulnerabilities of Location Privacy Mechanisms...
Conference talk: Understanding Vulnerabilities of Location Privacy Mechanisms...Conference talk: Understanding Vulnerabilities of Location Privacy Mechanisms...
Conference talk: Understanding Vulnerabilities of Location Privacy Mechanisms...
 
Mobile gaming 2009 an abstract location model
Mobile gaming 2009   an abstract location modelMobile gaming 2009   an abstract location model
Mobile gaming 2009 an abstract location model
 
understanding the planet using satellites and deep learning
understanding the planet using satellites and deep learningunderstanding the planet using satellites and deep learning
understanding the planet using satellites and deep learning
 
Modeling Crowds in Urban Spaces
Modeling Crowds in Urban SpacesModeling Crowds in Urban Spaces
Modeling Crowds in Urban Spaces
 
AI Presentation 1
AI Presentation 1AI Presentation 1
AI Presentation 1
 
90seconds Presentation
90seconds Presentation90seconds Presentation
90seconds Presentation
 
Integrated Hidden Markov Model and Kalman Filter for Online Object Tracking
Integrated Hidden Markov Model and Kalman Filter for Online Object TrackingIntegrated Hidden Markov Model and Kalman Filter for Online Object Tracking
Integrated Hidden Markov Model and Kalman Filter for Online Object Tracking
 
Embedded Sensing and Computational Behaviour Science
Embedded Sensing and Computational Behaviour ScienceEmbedded Sensing and Computational Behaviour Science
Embedded Sensing and Computational Behaviour Science
 
Contextual Dissonance: Design Bias in Sensor-Based Experience Sampling Methods
Contextual Dissonance: Design Bias in Sensor-Based Experience Sampling MethodsContextual Dissonance: Design Bias in Sensor-Based Experience Sampling Methods
Contextual Dissonance: Design Bias in Sensor-Based Experience Sampling Methods
 
Transforming instagram data into location intelligence
Transforming instagram data into location intelligenceTransforming instagram data into location intelligence
Transforming instagram data into location intelligence
 
Semantic Sensor Networks and Linked Stream Data
Semantic Sensor Networks and Linked Stream DataSemantic Sensor Networks and Linked Stream Data
Semantic Sensor Networks and Linked Stream Data
 
Human activity recognition updated 1 - Copy.pptx
Human activity recognition updated 1 - Copy.pptxHuman activity recognition updated 1 - Copy.pptx
Human activity recognition updated 1 - Copy.pptx
 
Gj3511231126
Gj3511231126Gj3511231126
Gj3511231126
 
Enhancing indoor localization using IoT techniques
Enhancing indoor localization using IoT techniquesEnhancing indoor localization using IoT techniques
Enhancing indoor localization using IoT techniques
 

More from PyData

Michal Mucha: Build and Deploy an End-to-end Streaming NLP Insight System | P...
Michal Mucha: Build and Deploy an End-to-end Streaming NLP Insight System | P...Michal Mucha: Build and Deploy an End-to-end Streaming NLP Insight System | P...
Michal Mucha: Build and Deploy an End-to-end Streaming NLP Insight System | P...PyData
 
Unit testing data with marbles - Jane Stewart Adams, Leif Walsh
Unit testing data with marbles - Jane Stewart Adams, Leif WalshUnit testing data with marbles - Jane Stewart Adams, Leif Walsh
Unit testing data with marbles - Jane Stewart Adams, Leif WalshPyData
 
The TileDB Array Data Storage Manager - Stavros Papadopoulos, Jake Bolewski
The TileDB Array Data Storage Manager - Stavros Papadopoulos, Jake BolewskiThe TileDB Array Data Storage Manager - Stavros Papadopoulos, Jake Bolewski
The TileDB Array Data Storage Manager - Stavros Papadopoulos, Jake BolewskiPyData
 
Using Embeddings to Understand the Variance and Evolution of Data Science... ...
Using Embeddings to Understand the Variance and Evolution of Data Science... ...Using Embeddings to Understand the Variance and Evolution of Data Science... ...
Using Embeddings to Understand the Variance and Evolution of Data Science... ...PyData
 
Deploying Data Science for Distribution of The New York Times - Anne Bauer
Deploying Data Science for Distribution of The New York Times - Anne BauerDeploying Data Science for Distribution of The New York Times - Anne Bauer
Deploying Data Science for Distribution of The New York Times - Anne BauerPyData
 
Graph Analytics - From the Whiteboard to Your Toolbox - Sam Lerma
Graph Analytics - From the Whiteboard to Your Toolbox - Sam LermaGraph Analytics - From the Whiteboard to Your Toolbox - Sam Lerma
Graph Analytics - From the Whiteboard to Your Toolbox - Sam LermaPyData
 
Do Your Homework! Writing tests for Data Science and Stochastic Code - David ...
Do Your Homework! Writing tests for Data Science and Stochastic Code - David ...Do Your Homework! Writing tests for Data Science and Stochastic Code - David ...
Do Your Homework! Writing tests for Data Science and Stochastic Code - David ...PyData
 
RESTful Machine Learning with Flask and TensorFlow Serving - Carlo Mazzaferro
RESTful Machine Learning with Flask and TensorFlow Serving - Carlo MazzaferroRESTful Machine Learning with Flask and TensorFlow Serving - Carlo Mazzaferro
RESTful Machine Learning with Flask and TensorFlow Serving - Carlo MazzaferroPyData
 
Mining dockless bikeshare and dockless scootershare trip data - Stefanie Brod...
Mining dockless bikeshare and dockless scootershare trip data - Stefanie Brod...Mining dockless bikeshare and dockless scootershare trip data - Stefanie Brod...
Mining dockless bikeshare and dockless scootershare trip data - Stefanie Brod...PyData
 
Avoiding Bad Database Surprises: Simulation and Scalability - Steven Lott
Avoiding Bad Database Surprises: Simulation and Scalability - Steven LottAvoiding Bad Database Surprises: Simulation and Scalability - Steven Lott
Avoiding Bad Database Surprises: Simulation and Scalability - Steven LottPyData
 
Words in Space - Rebecca Bilbro
Words in Space - Rebecca BilbroWords in Space - Rebecca Bilbro
Words in Space - Rebecca BilbroPyData
 
End-to-End Machine learning pipelines for Python driven organizations - Nick ...
End-to-End Machine learning pipelines for Python driven organizations - Nick ...End-to-End Machine learning pipelines for Python driven organizations - Nick ...
End-to-End Machine learning pipelines for Python driven organizations - Nick ...PyData
 
Pydata beautiful soup - Monica Puerto
Pydata beautiful soup - Monica PuertoPydata beautiful soup - Monica Puerto
Pydata beautiful soup - Monica PuertoPyData
 
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...PyData
 
Extending Pandas with Custom Types - Will Ayd
Extending Pandas with Custom Types - Will AydExtending Pandas with Custom Types - Will Ayd
Extending Pandas with Custom Types - Will AydPyData
 
Measuring Model Fairness - Stephen Hoover
Measuring Model Fairness - Stephen HooverMeasuring Model Fairness - Stephen Hoover
Measuring Model Fairness - Stephen HooverPyData
 
What's the Science in Data Science? - Skipper Seabold
What's the Science in Data Science? - Skipper SeaboldWhat's the Science in Data Science? - Skipper Seabold
What's the Science in Data Science? - Skipper SeaboldPyData
 
Applying Statistical Modeling and Machine Learning to Perform Time-Series For...
Applying Statistical Modeling and Machine Learning to Perform Time-Series For...Applying Statistical Modeling and Machine Learning to Perform Time-Series For...
Applying Statistical Modeling and Machine Learning to Perform Time-Series For...PyData
 
Solving very simple substitution ciphers algorithmically - Stephen Enright-Ward
Solving very simple substitution ciphers algorithmically - Stephen Enright-WardSolving very simple substitution ciphers algorithmically - Stephen Enright-Ward
Solving very simple substitution ciphers algorithmically - Stephen Enright-WardPyData
 
The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...
The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...
The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...PyData
 

More from PyData (20)

Michal Mucha: Build and Deploy an End-to-end Streaming NLP Insight System | P...
Michal Mucha: Build and Deploy an End-to-end Streaming NLP Insight System | P...Michal Mucha: Build and Deploy an End-to-end Streaming NLP Insight System | P...
Michal Mucha: Build and Deploy an End-to-end Streaming NLP Insight System | P...
 
Unit testing data with marbles - Jane Stewart Adams, Leif Walsh
Unit testing data with marbles - Jane Stewart Adams, Leif WalshUnit testing data with marbles - Jane Stewart Adams, Leif Walsh
Unit testing data with marbles - Jane Stewart Adams, Leif Walsh
 
The TileDB Array Data Storage Manager - Stavros Papadopoulos, Jake Bolewski
The TileDB Array Data Storage Manager - Stavros Papadopoulos, Jake BolewskiThe TileDB Array Data Storage Manager - Stavros Papadopoulos, Jake Bolewski
The TileDB Array Data Storage Manager - Stavros Papadopoulos, Jake Bolewski
 
Using Embeddings to Understand the Variance and Evolution of Data Science... ...
Using Embeddings to Understand the Variance and Evolution of Data Science... ...Using Embeddings to Understand the Variance and Evolution of Data Science... ...
Using Embeddings to Understand the Variance and Evolution of Data Science... ...
 
Deploying Data Science for Distribution of The New York Times - Anne Bauer
Deploying Data Science for Distribution of The New York Times - Anne BauerDeploying Data Science for Distribution of The New York Times - Anne Bauer
Deploying Data Science for Distribution of The New York Times - Anne Bauer
 
Graph Analytics - From the Whiteboard to Your Toolbox - Sam Lerma
Graph Analytics - From the Whiteboard to Your Toolbox - Sam LermaGraph Analytics - From the Whiteboard to Your Toolbox - Sam Lerma
Graph Analytics - From the Whiteboard to Your Toolbox - Sam Lerma
 
Do Your Homework! Writing tests for Data Science and Stochastic Code - David ...
Do Your Homework! Writing tests for Data Science and Stochastic Code - David ...Do Your Homework! Writing tests for Data Science and Stochastic Code - David ...
Do Your Homework! Writing tests for Data Science and Stochastic Code - David ...
 
RESTful Machine Learning with Flask and TensorFlow Serving - Carlo Mazzaferro
RESTful Machine Learning with Flask and TensorFlow Serving - Carlo MazzaferroRESTful Machine Learning with Flask and TensorFlow Serving - Carlo Mazzaferro
RESTful Machine Learning with Flask and TensorFlow Serving - Carlo Mazzaferro
 
Mining dockless bikeshare and dockless scootershare trip data - Stefanie Brod...
Mining dockless bikeshare and dockless scootershare trip data - Stefanie Brod...Mining dockless bikeshare and dockless scootershare trip data - Stefanie Brod...
Mining dockless bikeshare and dockless scootershare trip data - Stefanie Brod...
 
Avoiding Bad Database Surprises: Simulation and Scalability - Steven Lott
Avoiding Bad Database Surprises: Simulation and Scalability - Steven LottAvoiding Bad Database Surprises: Simulation and Scalability - Steven Lott
Avoiding Bad Database Surprises: Simulation and Scalability - Steven Lott
 
Words in Space - Rebecca Bilbro
Words in Space - Rebecca BilbroWords in Space - Rebecca Bilbro
Words in Space - Rebecca Bilbro
 
End-to-End Machine learning pipelines for Python driven organizations - Nick ...
End-to-End Machine learning pipelines for Python driven organizations - Nick ...End-to-End Machine learning pipelines for Python driven organizations - Nick ...
End-to-End Machine learning pipelines for Python driven organizations - Nick ...
 
Pydata beautiful soup - Monica Puerto
Pydata beautiful soup - Monica PuertoPydata beautiful soup - Monica Puerto
Pydata beautiful soup - Monica Puerto
 
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
 
Extending Pandas with Custom Types - Will Ayd
Extending Pandas with Custom Types - Will AydExtending Pandas with Custom Types - Will Ayd
Extending Pandas with Custom Types - Will Ayd
 
Measuring Model Fairness - Stephen Hoover
Measuring Model Fairness - Stephen HooverMeasuring Model Fairness - Stephen Hoover
Measuring Model Fairness - Stephen Hoover
 
What's the Science in Data Science? - Skipper Seabold
What's the Science in Data Science? - Skipper SeaboldWhat's the Science in Data Science? - Skipper Seabold
What's the Science in Data Science? - Skipper Seabold
 
Applying Statistical Modeling and Machine Learning to Perform Time-Series For...
Applying Statistical Modeling and Machine Learning to Perform Time-Series For...Applying Statistical Modeling and Machine Learning to Perform Time-Series For...
Applying Statistical Modeling and Machine Learning to Perform Time-Series For...
 
Solving very simple substitution ciphers algorithmically - Stephen Enright-Ward
Solving very simple substitution ciphers algorithmically - Stephen Enright-WardSolving very simple substitution ciphers algorithmically - Stephen Enright-Ward
Solving very simple substitution ciphers algorithmically - Stephen Enright-Ward
 
The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...
The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...
The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...
 

Recently uploaded

GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersThousandEyes
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
Google AI Hackathon: LLM based Evaluator for RAG
Google AI Hackathon: LLM based Evaluator for RAGGoogle AI Hackathon: LLM based Evaluator for RAG
Google AI Hackathon: LLM based Evaluator for RAGSujit Pal
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 

Recently uploaded (20)

GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
Google AI Hackathon: LLM based Evaluator for RAG
Google AI Hackathon: LLM based Evaluator for RAGGoogle AI Hackathon: LLM based Evaluator for RAG
Google AI Hackathon: LLM based Evaluator for RAG
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 

Measuring and Predicting Departures from Routine in Human Mobility by Dirk Gorissen

  • 1. Measuring and Predicting Departures from Routine in Human Mobility Dirk Gorissen | @elazungu PyData London - 23 February 2014
  • 3. Human Mobility - Credits  University of Southampton  James McInerney  Sebastian Stein  Alex Rogers  Nick Jennings  BAE Systems ATC  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
  • 4.  Beijing Taxi rides  Nicholas Jing Yuan (Microsoft Research)
  • 5. Human Mobility  London in Motion - Jay Gordon (MIT)
  • 6. Human Mobility: Inference  Functional Regions of a city  Nicholas Jing Yuan (Microsoft Research)
  • 7. Human Mobility: Inference  Jay Gordon (MIT)
  • 8. Human Mobility: Inference  Cross cuts many fields: sociology, physics, network theory, computer science, epidemiology, … © PNAS © MIT
  • 9. Project InMind  Project InMind announced on 12 Feb  $10m Yahoo-CMU collaboration on predicting human needs and intentions
  • 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.”
  • 11. Temporal Regularity  [Herder 2012] [Song 2010]
  • 12. Spatial Regularity  [Herder 2012] [Song 2010]
  • 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
  • 15. Human Mobility: Inference  London riots “commute”
  • 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
  • 18. Bayesian Networks  Bottom up: Grass is wet, what is the most likely cause?  Top down: Its cloudy, what is the probability the grass is wet?
  • 19. Hidden Markov Model  Simple Dynamic Bayesian Network  Shaded nodes are observed
  • 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
  • 21. Probabilistic Models  Model can be run backwards  Backwards (Inference): data -> parameters
  • 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
  • 26. Sensors  Noisy sensors, e.g., cell tower observations  observed: latitude/longitude  inferred: variance (of locations)
  • 27. Reported Variance  E.g., GPS  observed: latitude/longitude, variance
  • 28. Trustworthiness  E.g., Eyewitness  observed: latitude/longitude, reported variance  inferred: trustworthiness of observation  single latent trust value(per time step & source)
  • 31. Inference is Challenging  Exact inference intractable  Can perform approximate inference using:  Expectation maximisation algorithm  Fast  But point estimates of parameters  Gibbs sampling, or other Markov chain Monte Carlo  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
  • 33. Model enables  Inference  location  departures from routine  noise characteristics of observations  trust characteristics of sensors  Exploration/summarisation  parameters have intuitive interpretations  Prediction  Future mobility (given time context)  Future departures from routine
  • 34. Performance  Nokia Dataset (GPS only) [McInerney 2012]
  • 36. Performance  Synthetic dataset with heterogeneous, untrustworthy observations.  Parameters of generating model learned from OpenPaths dataset
  • 38. Implementation  Backend inference and data processing code all python  numpy  scipy  matplotlib  UI to explore model predictions & sanity check  flask  d3.js  leaflet.js  kockout.js  Future  Gensim, pymc, bayespy, …  Probabilistic programming
  • 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
  • 46. Questions?  Thank you.  dirk.gorissen@baesystems.com | @elazungu  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.

Editor's Notes

  1. http://www.pnas.org/content/95/25/15145/F2.expansion.htmlhttps://cee.mit.edu/news/releases/2013/human-mobility-travel-configurations
  2. http://ceur-ws.org/Vol-872/aum2012_paper_3.pdf