Friendship and Mobility: User Movement In Location-Based Social Networks. Eunjoon Cho* Seth A. Myers* Jure Leskovec

Size: px
Start display at page:

Download "Friendship and Mobility: User Movement In Location-Based Social Networks. Eunjoon Cho* Seth A. Myers* Jure Leskovec"

Transcription

1 Friendship and Mobility: User Movement In Location-Based Social Networks Eunjoon Cho* Seth A. Myers* Jure Leskovec

2 Outline Introduction Related Work Data Observations from Data Model of Human Mobility Evaluation Summary

3 Introduction Human Mobility patterns have: A high degree of freedom and variation Show structural patterns due to: Geographic constraints Social constraints Short-ranged Travel is Periodic spatially and temporally Not affected by social network ties Long-distance Travel is influenced by social network ties

4 Introduction Contd.. Aim: To identify fundamental factors that govern Human Mobility. To develop a human mobility model capturing: Short-ranged Travel due to work Long-distance Travel due to social network To find answers to some interesting questions: Does mobility have an effect on human friendship? Does friendship have an effect on human mobility? Are people s visits periodic?

5 Introduction Contd.. Hypothesis: Mobility is, Periodic between home and work Constrained by distance travelable in a day Shaped by social relationships

6 Introduction Contd.. Hypothesis: Mobility is, Periodic between home and work Constrained by distance travelable in a day Shaped by social relationships Can be tested using check-ins from: Location Based Social Networks (Eg. Gowalla and Brightkite) Cellphone data

7 Introduction Contd.. Importance: Mobility Modelling is important for Urban Planning Understanding of Human Migration Patterns and spread of diseases Improving location based recommendations

8 Related Work Two categories of related work: Common Limitation: Do not consider geographic movement, temporal dynamics and social network together to build a model. Models of Human movement and Dynamics Consider mobility as a stochastic process centered about one fixed point Drawback: Poor accuracy Solution: Consider mobility a stochastic process around several fixed points Use wireless network or GPS data to model mobility Drawback: Studies limited to small geographic area (eg., college campus) Studies on impact of geography on social interaction

9 Data Cellphone Gowalla Brightkite Users 2,000, ,591 58,288 Friendships 4,500, , ,078 Check-ins 900,000,000 6,400,000 4,500,000

10 Data Contd.. Cellphone Social Media (Gowalla and Brightkite) Coarse location accuracy Implicit and frequent check-ins Implicit Social Network Data from one unnamed country Good location accuracy Explicit and sporadic check-ins Explicit Social Network Data from across the World

11 Data Contd.. Definitions for Cellphone Data: Check-in: Location and time of a phone call Friends: People who have called each other at least five times Home: Average position of check-ins in the cell with most check-ins Cell: 25km x 25km area section from a discretized world

12 Observations from Data

13 Observations from Data Kink at 100 Km mark!

14 Observations from Data Kink at 100 Km mark! Explained by: Non-uniform population distribution Radius of reach"

15 Observations from Data Contd..

16 Observations from Data Contd..

17 Observations from Data Contd.. Where P null (d) is the probability of being around a friend s home, given, movement is random with respect to population density.

18 Observations from Data Contd Where P null (d) is the probability of being around a friend s home, given, movement is random with respect to population density.

19 Observations from Data Contd.. Influence Graph 0.3 Where P null (d) is the probability of being around a friend s home, given, movement is random with respect to population density.

20 Observations from Data Contd.. Influence of friends on individual s mobility Friendship causing mobility Network before time t 1 considered Fraction of check-ins near friends in this network calculated 61% probability that a user visits a friend Mobility causing friendship Check-ins before time t 1 considered New friends created by these check-ins calculated 24% probability that a check-in will lead to new friendship

21 Observations from Data Contd.. Limits of using friendship to predict mobility

22 Observations from Data Contd.. Limits of using friendship to predict mobility %

23 Observations from Data Contd.. Limits of using friendship to predict mobility Element of time considered % 40%

24 Observations from Data Contd.. Temporal and geographic periodicity

25 Observations from Data Contd.. Temporal and geographic periodicity Evening Weekend Evening Weekend Morning Morning

26 Observations from Data Contd.. More Observations Brightkite 53% of check-ins in Brightkite previously visited by user Only 4.1% of check-ins previously visited by a friend Gowalla 31% of check-ins previously visited by user Only 9.6% of check-ins previously visited by a friend

27 Model of Human Mobility Periodic Mobility Model (PMM): Assuming Movement is based on periodic movement between two states (Home and Work) Probability Definition: Where, x u (t) is location of user u time t c u (t) is state of user u time t

28 Model of Human Mobility Contd.. Check-in of a user in San Fransicso (Red:Home, Blue:Work)

29 Model of Human Mobility Contd.. Temporal Component of PMM Model: Truncated Gaussian Distribution

30 Model of Human Mobility Contd.. Spatial Component of PMM Model: 2-dimensional time-independent Gaussian Distribution

31 Model of Human Mobility Contd.. Hence, PMM Model is: A two state mixture of Gaussians with time dependent state prior.

32 Model of Human Mobility Contd.. Hence, PMM Model is: A two state mixture of Gaussians with time dependent state prior. Probability density of user location over time from work to home in PMM

33 Model of Human Mobility Contd.. Periodic and Social Mobility Model (PSMM): Assuming Movement is based on movement between three states (Home, Work and Outlier). It captures both the non-periodic (social) movement and periodic movement. Probability Definition: Where, z u (t)=1 means check-in is social (non-periodic) z u (t)=0 means check-in is periodic

34 Model of Human Mobility Contd.. is the same as PMM (Periodic Mobility Model) Where J u is the set of check-ins by u s friends in the same day

35 Model of Human Mobility Contd.. Decay of Probability of a location based on time difference and distance from a friend s check-in

36 Model of Human Mobility Contd.. Fitting PMM and PSMM models: PMM: PSMM: Fitted using Random restart Expectation Maximization (EM) Overfitting avoided using regularization Minimum singular value of spatial covariance is set as 10-7 Minimum bound on temporal variance is set as 10-4 Train PMM with three latent states: home, work and outlier Fit social model to the outlier check-ins Fitting of decay variables, alpha and beta, done using (EM) for each user

37 Evaluation of PMM and PSMM Metrics used: Predictive Accuracy Average Log Likelihood Relative Expected Distance Error

38 Evaluation of PMM and PSMM Metrics used: Predictive Accuracy : Accuracy of exact prediction Average Log Likelihood Relative Expected Distance Error

39 Evaluation of PMM and PSMM Metrics used: Predictive Accuracy : Accuracy of exact prediction Average Log Likelihood : Fitment of test set in model Relative Expected Distance Error

40 Evaluation of PMM and PSMM Metrics used: Predictive Accuracy : Accuracy of exact prediction Average Log Likelihood : Fitment of test set in model Relative Expected Distance Error : (Expected Distance Error) / (Radius of Gyration of a user in a day) Where Expected Distance Error is:

41 Evaluation of PMM and PSMM Contd.. Baselines used: Most Frequented Location Model (MF): Probability is proportional to fraction of check-ins in that location at the same hour on previous days

42 Evaluation of PMM and PSMM Contd.. Baselines used: Gaussian Model (G): Probability is given by Gaussian distribution of check-ins on the same day of previous weeks centered around a single point RW Model: Predicts check-in location as last known check-in location

43 Evaluation of PMM and PSMM Contd.. `

44 Evaluation of PMM and PSMM Contd..

45 Evaluation of PMM and PSMM Contd..

46 Evaluation of PMM and PSMM Contd.. Similarity of Daily mobility patterns Similarity metric:

47 Evaluation of PMM and PSMM Contd..

48 Evaluation of PMM and PSMM Contd..

49 Evaluation of PMM and PSMM Contd..

50 Evaluation of PMM and PSMM Contd..

51 Evaluation of PMM and PSMM Contd.. Number of Latent States Accuracy % % %

52 Summary Social relationships can explain 10% to 30% of human movement Periodic behavior can explain 50% to 70% of human movement Short-range travel is periodic and not affected by social ties People are more likely to visit a distant place if a friend lives there Influence of friendship on mobility is 2x stronger than influence of mobility on friendship People are 5 times more likely to visit a place they previously visited than to visit a place previously visited by a friend The model captures both periodic short-range travel and social ties based long-distance travel The model can predict high precision user location with 40% accuracy Performance gained by adding additional latent states after 3 has marginal effect on accuracy

53 Thank You

Point-of-Interest Recommendations: Learning Potential Check-ins from Friends

Point-of-Interest Recommendations: Learning Potential Check-ins from Friends Point-of-Interest Recommendations: Learning Potential Check-ins from Friends Huayu Li, Yong Ge +, Richang Hong, Hengshu Zhu University of North Carolina at Charlotte + University of Arizona Hefei University

More information

Inferring Friendship from Check-in Data of Location-Based Social Networks

Inferring Friendship from Check-in Data of Location-Based Social Networks Inferring Friendship from Check-in Data of Location-Based Social Networks Ran Cheng, Jun Pang, Yang Zhang Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg, Luxembourg

More information

Exploiting Geographic Dependencies for Real Estate Appraisal

Exploiting Geographic Dependencies for Real Estate Appraisal Exploiting Geographic Dependencies for Real Estate Appraisal Yanjie Fu Joint work with Hui Xiong, Yu Zheng, Yong Ge, Zhihua Zhou, Zijun Yao Rutgers, the State University of New Jersey Microsoft Research

More information

Learning to Recommend Point-of-Interest with the Weighted Bayesian Personalized Ranking Method in LBSNs

Learning to Recommend Point-of-Interest with the Weighted Bayesian Personalized Ranking Method in LBSNs information Article Learning to Recommend Point-of-Interest with the Weighted Bayesian Personalized Ranking Method in LBSNs Lei Guo 1, *, Haoran Jiang 2, Xinhua Wang 3 and Fangai Liu 3 1 School of Management

More information

Social and Technological Network Analysis: Spatial Networks, Mobility and Applications

Social and Technological Network Analysis: Spatial Networks, Mobility and Applications Social and Technological Network Analysis: Spatial Networks, Mobility and Applications Anastasios Noulas Computer Laboratory, University of Cambridge February 2015 Today s Outline 1. Introduction to spatial

More information

Aggregated Temporal Tensor Factorization Model for Point-of-interest Recommendation

Aggregated Temporal Tensor Factorization Model for Point-of-interest Recommendation Aggregated Temporal Tensor Factorization Model for Point-of-interest Recommendation Shenglin Zhao 1,2B, Michael R. Lyu 1,2, and Irwin King 1,2 1 Shenzhen Key Laboratory of Rich Media Big Data Analytics

More information

Regularity and Conformity: Location Prediction Using Heterogeneous Mobility Data

Regularity and Conformity: Location Prediction Using Heterogeneous Mobility Data Regularity and Conformity: Location Prediction Using Heterogeneous Mobility Data Yingzi Wang 12, Nicholas Jing Yuan 2, Defu Lian 3, Linli Xu 1 Xing Xie 2, Enhong Chen 1, Yong Rui 2 1 University of Science

More information

Location Regularization-Based POI Recommendation in Location-Based Social Networks

Location Regularization-Based POI Recommendation in Location-Based Social Networks information Article Location Regularization-Based POI Recommendation in Location-Based Social Networks Lei Guo 1,2, * ID, Haoran Jiang 3 and Xinhua Wang 4 1 Postdoctoral Research Station of Management

More information

Social and Technological Network Analysis. Lecture 11: Spa;al and Social Network Analysis. Dr. Cecilia Mascolo

Social and Technological Network Analysis. Lecture 11: Spa;al and Social Network Analysis. Dr. Cecilia Mascolo Social and Technological Network Analysis Lecture 11: Spa;al and Social Network Analysis Dr. Cecilia Mascolo In This Lecture In this lecture we will study spa;al networks and geo- social networks through

More information

Introduction to Graphical Models

Introduction to Graphical Models Introduction to Graphical Models The 15 th Winter School of Statistical Physics POSCO International Center & POSTECH, Pohang 2018. 1. 9 (Tue.) Yung-Kyun Noh GENERALIZATION FOR PREDICTION 2 Probabilistic

More information

Detecting Origin-Destination Mobility Flows From Geotagged Tweets in Greater Los Angeles Area

Detecting Origin-Destination Mobility Flows From Geotagged Tweets in Greater Los Angeles Area Detecting Origin-Destination Mobility Flows From Geotagged Tweets in Greater Los Angeles Area Song Gao 1, Jiue-An Yang 1,2, Bo Yan 1, Yingjie Hu 1, Krzysztof Janowicz 1, Grant McKenzie 1 1 STKO Lab, Department

More information

A route map to calibrate spatial interaction models from GPS movement data

A route map to calibrate spatial interaction models from GPS movement data A route map to calibrate spatial interaction models from GPS movement data K. Sila-Nowicka 1, A.S. Fotheringham 2 1 Urban Big Data Centre School of Political and Social Sciences University of Glasgow Lilybank

More information

Collaborative Location Recommendation by Integrating Multi-dimensional Contextual Information

Collaborative Location Recommendation by Integrating Multi-dimensional Contextual Information 1 Collaborative Location Recommendation by Integrating Multi-dimensional Contextual Information LINA YAO, University of New South Wales QUAN Z. SHENG, Macquarie University XIANZHI WANG, Singapore Management

More information

Spatial Epidemic Modelling in Social Networks

Spatial Epidemic Modelling in Social Networks Spatial Epidemic Modelling in Social Networks Joana Margarida Simoes Centre for Advanced Spatial Analysis, University College of London, UK Abstract. The spread of infectious diseases is highly influenced

More information

Human Mobility Pattern Prediction Algorithm using Mobile Device Location and Time Data

Human Mobility Pattern Prediction Algorithm using Mobile Device Location and Time Data Human Mobility Pattern Prediction Algorithm using Mobile Device Location and Time Data 0. Notations Myungjun Choi, Yonghyun Ro, Han Lee N = number of states in the model T = length of observation sequence

More information

Exploring the Patterns of Human Mobility Using Heterogeneous Traffic Trajectory Data

Exploring the Patterns of Human Mobility Using Heterogeneous Traffic Trajectory Data Exploring the Patterns of Human Mobility Using Heterogeneous Traffic Trajectory Data Jinzhong Wang April 13, 2016 The UBD Group Mobile and Social Computing Laboratory School of Software, Dalian University

More information

Bayesian Regression (1/31/13)

Bayesian Regression (1/31/13) STA613/CBB540: Statistical methods in computational biology Bayesian Regression (1/31/13) Lecturer: Barbara Engelhardt Scribe: Amanda Lea 1 Bayesian Paradigm Bayesian methods ask: given that I have observed

More information

Link Prediction. Eman Badr Mohammed Saquib Akmal Khan

Link Prediction. Eman Badr Mohammed Saquib Akmal Khan Link Prediction Eman Badr Mohammed Saquib Akmal Khan 11-06-2013 Link Prediction Which pair of nodes should be connected? Applications Facebook friend suggestion Recommendation systems Monitoring and controlling

More information

Time-aware Point-of-interest Recommendation

Time-aware Point-of-interest Recommendation Time-aware Point-of-interest Recommendation Quan Yuan, Gao Cong, Zongyang Ma, Aixin Sun, and Nadia Magnenat-Thalmann School of Computer Engineering Nanyang Technological University Presented by ShenglinZHAO

More information

Socio-spatial Properties of Online Location-based Social Networks

Socio-spatial Properties of Online Location-based Social Networks Socio-spatial Properties of Online Location-based Social Networks Salvatore Scellato Computer Laboratory University of Cambridge salvatore.scellato@cam.ac.uk Renaud Lambiotte Deparment of Mathematics Imperial

More information

Not All Apps Are Created Equal:

Not All Apps Are Created Equal: Not All Apps Are Created Equal: Analysis of Spatiotemporal Heterogeneity in Nationwide Mobile Service Usage Cristina Marquez and Marco Gramaglia (Universidad Carlos III de Madrid); Marco Fiore (CNR-IEIIT);

More information

Discovering Urban Spatial-Temporal Structure from Human Activity Patterns

Discovering Urban Spatial-Temporal Structure from Human Activity Patterns ACM SIGKDD International Workshop on Urban Computing (UrbComp 2012) Discovering Urban Spatial-Temporal Structure from Human Activity Patterns Shan Jiang, shanjang@mit.edu Joseph Ferreira, Jr., jf@mit.edu

More information

Kristina Lerman USC Information Sciences Institute

Kristina Lerman USC Information Sciences Institute Rethinking Network Structure Kristina Lerman USC Information Sciences Institute Università della Svizzera Italiana, December 16, 2011 Measuring network structure Central nodes Community structure Strength

More information

Matrix Factorization Techniques for Recommender Systems

Matrix Factorization Techniques for Recommender Systems Matrix Factorization Techniques for Recommender Systems Patrick Seemann, December 16 th, 2014 16.12.2014 Fachbereich Informatik Recommender Systems Seminar Patrick Seemann Topics Intro New-User / New-Item

More information

Obtaining Critical Values for Test of Markov Regime Switching

Obtaining Critical Values for Test of Markov Regime Switching University of California, Santa Barbara From the SelectedWorks of Douglas G. Steigerwald November 1, 01 Obtaining Critical Values for Test of Markov Regime Switching Douglas G Steigerwald, University of

More information

Validating general human mobility patterns on massive GPS data

Validating general human mobility patterns on massive GPS data Validating general human mobility patterns on massive GPS data Luca Pappalardo, Salvatore Rinzivillo, Dino Pedreschi, and Fosca Giannotti KDDLab, Institute of Information Science and Technologies (ISTI),

More information

STA 4273H: Statistical Machine Learning

STA 4273H: Statistical Machine Learning STA 4273H: Statistical Machine Learning Russ Salakhutdinov Department of Statistics! rsalakhu@utstat.toronto.edu! http://www.utstat.utoronto.ca/~rsalakhu/ Sidney Smith Hall, Room 6002 Lecture 11 Project

More information

Web Structure Mining Nodes, Links and Influence

Web Structure Mining Nodes, Links and Influence Web Structure Mining Nodes, Links and Influence 1 Outline 1. Importance of nodes 1. Centrality 2. Prestige 3. Page Rank 4. Hubs and Authority 5. Metrics comparison 2. Link analysis 3. Influence model 1.

More information

Spatial Web Technology for Urban Green Society (A Case of Tsukuba City)

Spatial Web Technology for Urban Green Society (A Case of Tsukuba City) The 5th Japan-Korea-China Joint Conference on Geography (Green Society in East Asia: A Geographical Contribution) Spatial Web Technology for Urban Green Society (A Case of Tsukuba City) Ko Ko Lwin and

More information

Lecture 11: Unsupervised Machine Learning

Lecture 11: Unsupervised Machine Learning CSE517A Machine Learning Spring 2018 Lecture 11: Unsupervised Machine Learning Instructor: Marion Neumann Scribe: Jingyu Xin Reading: fcml Ch6 (Intro), 6.2 (k-means), 6.3 (Mixture Models); [optional]:

More information

Your web browser (Safari 7) is out of date. For more security, comfort and. the best experience on this site: Update your browser Ignore

Your web browser (Safari 7) is out of date. For more security, comfort and. the best experience on this site: Update your browser Ignore Your web browser (Safari 7) is out of date. For more security, comfort and Activityengage the best experience on this site: Update your browser Ignore Introduction to GIS What is a geographic information

More information

CSC2515 Winter 2015 Introduction to Machine Learning. Lecture 2: Linear regression

CSC2515 Winter 2015 Introduction to Machine Learning. Lecture 2: Linear regression CSC2515 Winter 2015 Introduction to Machine Learning Lecture 2: Linear regression All lecture slides will be available as.pdf on the course website: http://www.cs.toronto.edu/~urtasun/courses/csc2515/csc2515_winter15.html

More information

Lessons From the Trenches: using Mobile Phone Data for Official Statistics

Lessons From the Trenches: using Mobile Phone Data for Official Statistics Lessons From the Trenches: using Mobile Phone Data for Official Statistics Maarten Vanhoof Orange Labs/Newcastle University M.vanhoof1@newcastle.ac.uk @Metti Hoof MaartenVanhoof.com Mobile Phone Data (Call

More information

Nature s Art Village

Nature s Art Village Nature s Art Village Educational Field Trip Programs Guide To: College, Career & Civic Life C3 Framework For Social Studies State Standards Grades 3 through 5 All That Glitters Children journey back in

More information

Diagnosing New York City s Noises with Ubiquitous Data

Diagnosing New York City s Noises with Ubiquitous Data Diagnosing New York City s Noises with Ubiquitous Data Dr. Yu Zheng yuzheng@microsoft.com Lead Researcher, Microsoft Research Chair Professor at Shanghai Jiao Tong University Background Many cities suffer

More information

* Matrix Factorization and Recommendation Systems

* Matrix Factorization and Recommendation Systems Matrix Factorization and Recommendation Systems Originally presented at HLF Workshop on Matrix Factorization with Loren Anderson (University of Minnesota Twin Cities) on 25 th September, 2017 15 th March,

More information

Collaborative topic models: motivations cont

Collaborative topic models: motivations cont Collaborative topic models: motivations cont Two topics: machine learning social network analysis Two people: " boy Two articles: article A! girl article B Preferences: The boy likes A and B --- no problem.

More information

COSMIC: COmplexity in Spatial dynamic

COSMIC: COmplexity in Spatial dynamic COSMIC: COmplexity in Spatial dynamic MICs 9 10 November, Brussels Michael Batty University College London m.batty@ucl.ac.uk http://www.casa.ucl.ac.uk/ Outline The Focus of the Pilot The Partners: VU,

More information

SQL-Rank: A Listwise Approach to Collaborative Ranking

SQL-Rank: A Listwise Approach to Collaborative Ranking SQL-Rank: A Listwise Approach to Collaborative Ranking Liwei Wu Depts of Statistics and Computer Science UC Davis ICML 18, Stockholm, Sweden July 10-15, 2017 Joint work with Cho-Jui Hsieh and James Sharpnack

More information

Geography 1103: Spatial Thinking

Geography 1103: Spatial Thinking Geography 1103: Spatial Thinking Lecture: T\TH 8:00-9:15 am (McEniry 401) Lab: Wed 2:00-4:30 pm (McEniry 420) Instructor: Dr. Elizabeth C. Delmelle Email: edelmell@uncc.edu Office: McEniry 419 Phone: 704-687-5932

More information

STA 414/2104: Machine Learning

STA 414/2104: Machine Learning STA 414/2104: Machine Learning Russ Salakhutdinov Department of Computer Science! Department of Statistics! rsalakhu@cs.toronto.edu! http://www.cs.toronto.edu/~rsalakhu/ Lecture 9 Sequential Data So far

More information

Uncovering the Digital Divide and the Physical Divide in Senegal Using Mobile Phone Data

Uncovering the Digital Divide and the Physical Divide in Senegal Using Mobile Phone Data Uncovering the Digital Divide and the Physical Divide in Senegal Using Mobile Phone Data Song Gao, Bo Yan, Li Gong, Blake Regalia, Yiting Ju, Yingjie Hu STKO Lab, Department of Geography, University of

More information

Learning Outbreak Regions in Bayesian Spatial Scan Statistics

Learning Outbreak Regions in Bayesian Spatial Scan Statistics Maxim Makatchev Daniel B. Neill Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh, PA 15213 USA maxim.makatchev@cs.cmu.edu neill@cs.cmu.edu Abstract The problem of anomaly detection for biosurveillance

More information

Exploring spatial decay effect in mass media and social media: a case study of China

Exploring spatial decay effect in mass media and social media: a case study of China Exploring spatial decay effect in mass media and social media: a case study of China 1. Introduction Yihong Yuan Department of Geography, Texas State University, San Marcos, TX, USA, 78666. Tel: +1(512)-245-3208

More information

Urban GIS for Health Metrics

Urban GIS for Health Metrics Urban GIS for Health Metrics Dajun Dai Department of Geosciences, Georgia State University Atlanta, Georgia, United States Presented at International Conference on Urban Health, March 5 th, 2014 People,

More information

Non-Inferiority Tests for the Ratio of Two Proportions in a Cluster- Randomized Design

Non-Inferiority Tests for the Ratio of Two Proportions in a Cluster- Randomized Design Chapter 236 Non-Inferiority Tests for the Ratio of Two Proportions in a Cluster- Randomized Design Introduction This module provides power analysis and sample size calculation for non-inferiority tests

More information

INTRODUCTION TO HUMAN GEOGRAPHY. Chapter 1

INTRODUCTION TO HUMAN GEOGRAPHY. Chapter 1 INTRODUCTION TO HUMAN GEOGRAPHY Chapter 1 What Is Human Geography? The study of How people make places How we organize space and society How we interact with each other in places and across space How we

More information

Urban characteristics attributable to density-driven tie formation

Urban characteristics attributable to density-driven tie formation Supplementary Information for Urban characteristics attributable to density-driven tie formation Wei Pan, Gourab Ghoshal, Coco Krumme, Manuel Cebrian, Alex Pentland S-1 T(ρ) 100000 10000 1000 100 theory

More information

STA 4273H: Statistical Machine Learning

STA 4273H: Statistical Machine Learning STA 4273H: Statistical Machine Learning Russ Salakhutdinov Department of Statistics! rsalakhu@utstat.toronto.edu! http://www.utstat.utoronto.ca/~rsalakhu/ Sidney Smith Hall, Room 6002 Lecture 7 Approximate

More information

Machine Learning for Data Science (CS4786) Lecture 12

Machine Learning for Data Science (CS4786) Lecture 12 Machine Learning for Data Science (CS4786) Lecture 12 Gaussian Mixture Models Course Webpage : http://www.cs.cornell.edu/courses/cs4786/2016fa/ Back to K-means Single link is sensitive to outliners We

More information

Interactive GIS in Veterinary Epidemiology Technology & Application in a Veterinary Diagnostic Lab

Interactive GIS in Veterinary Epidemiology Technology & Application in a Veterinary Diagnostic Lab Interactive GIS in Veterinary Epidemiology Technology & Application in a Veterinary Diagnostic Lab Basics GIS = Geographic Information System A GIS integrates hardware, software and data for capturing,

More information

Exploring Human Mobility with Multi-Source Data at Extremely Large Metropolitan Scales. ACM MobiCom 2014, Maui, HI

Exploring Human Mobility with Multi-Source Data at Extremely Large Metropolitan Scales. ACM MobiCom 2014, Maui, HI Exploring Human Mobility with Multi-Source Data at Extremely Large Metropolitan Scales Desheng Zhang & Tian He University of Minnesota, USA Jun Huang, Ye Li, Fan Zhang, Chengzhong Xu Shenzhen Institute

More information

Clustering. CSL465/603 - Fall 2016 Narayanan C Krishnan

Clustering. CSL465/603 - Fall 2016 Narayanan C Krishnan Clustering CSL465/603 - Fall 2016 Narayanan C Krishnan ckn@iitrpr.ac.in Supervised vs Unsupervised Learning Supervised learning Given x ", y " "%& ', learn a function f: X Y Categorical output classification

More information

Estimating Large Scale Population Movement ML Dublin Meetup

Estimating Large Scale Population Movement ML Dublin Meetup Deutsche Bank COO Chief Data Office Estimating Large Scale Population Movement ML Dublin Meetup John Doyle PhD Assistant Vice President CDO Research & Development Science & Innovation john.doyle@db.com

More information

Linear Dynamical Systems

Linear Dynamical Systems Linear Dynamical Systems Sargur N. srihari@cedar.buffalo.edu Machine Learning Course: http://www.cedar.buffalo.edu/~srihari/cse574/index.html Two Models Described by Same Graph Latent variables Observations

More information

Learning to Learn and Collaborative Filtering

Learning to Learn and Collaborative Filtering Appearing in NIPS 2005 workshop Inductive Transfer: Canada, December, 2005. 10 Years Later, Whistler, Learning to Learn and Collaborative Filtering Kai Yu, Volker Tresp Siemens AG, 81739 Munich, Germany

More information

Lecture 21: Spectral Learning for Graphical Models

Lecture 21: Spectral Learning for Graphical Models 10-708: Probabilistic Graphical Models 10-708, Spring 2016 Lecture 21: Spectral Learning for Graphical Models Lecturer: Eric P. Xing Scribes: Maruan Al-Shedivat, Wei-Cheng Chang, Frederick Liu 1 Motivation

More information

Restricted Boltzmann Machines for Collaborative Filtering

Restricted Boltzmann Machines for Collaborative Filtering Restricted Boltzmann Machines for Collaborative Filtering Authors: Ruslan Salakhutdinov Andriy Mnih Geoffrey Hinton Benjamin Schwehn Presentation by: Ioan Stanculescu 1 Overview The Netflix prize problem

More information

Machine Learning Linear Regression. Prof. Matteo Matteucci

Machine Learning Linear Regression. Prof. Matteo Matteucci Machine Learning Linear Regression Prof. Matteo Matteucci Outline 2 o Simple Linear Regression Model Least Squares Fit Measures of Fit Inference in Regression o Multi Variate Regession Model Least Squares

More information

Evaluation of urban mobility using surveillance cameras

Evaluation of urban mobility using surveillance cameras Procedia Computer Science Volume 66, 2015, Pages 364 371 YSC 2015. 4th International Young Scientists Conference on Computational Science Evaluation of urban mobility using surveillance cameras Alexey

More information

Overlapping Community Detection at Scale: A Nonnegative Matrix Factorization Approach

Overlapping Community Detection at Scale: A Nonnegative Matrix Factorization Approach Overlapping Community Detection at Scale: A Nonnegative Matrix Factorization Approach Author: Jaewon Yang, Jure Leskovec 1 1 Venue: WSDM 2013 Presenter: Yupeng Gu 1 Stanford University 1 Background Community

More information

Measuring User Similarity with Trajectory Patterns: Principles and New Metrics

Measuring User Similarity with Trajectory Patterns: Principles and New Metrics Measuring User Similarity with Trajectory Patterns: Principles and New Metrics Xihui hen 1, Ruipeng Lu 2, Xiaoxing Ma 3, and Jun Pang 1,2 1 Interdisciplinary entre for Security, Reliability and Trust,

More information

Unit 1 Review. Geography: Its Nature and Perspectives

Unit 1 Review. Geography: Its Nature and Perspectives Unit 1 Review Geography: Its Nature and Perspectives Agenda Test format Practice multiple choice questions Unit 1 in a nutshell Vocab game Test format 60 minutes: 75 multiple-choice questions Ten minute

More information

Space-adjusting Technologies and the Social Ecologies of Place

Space-adjusting Technologies and the Social Ecologies of Place Space-adjusting Technologies and the Social Ecologies of Place Donald G. Janelle University of California, Santa Barbara Reflections on Geographic Information Science Session in Honor of Michael Goodchild

More information

Research Methods II MICHAEL BERNSTEIN CS 376

Research Methods II MICHAEL BERNSTEIN CS 376 Research Methods II MICHAEL BERNSTEIN CS 376 Goal Understand and use statistical techniques common to HCI research 2 Last time How to plan an evaluation What is a statistical test? Chi-square t-test Paired

More information

Exploring the Association Between Family Planning and Developing Telecommunications Infrastructure in Rural Peru

Exploring the Association Between Family Planning and Developing Telecommunications Infrastructure in Rural Peru Exploring the Association Between Family Planning and Developing Telecommunications Infrastructure in Rural Peru Heide Jackson, University of Wisconsin-Madison September 21, 2011 Abstract This paper explores

More information

Lecture 6: Gaussian Mixture Models (GMM)

Lecture 6: Gaussian Mixture Models (GMM) Helsinki Institute for Information Technology Lecture 6: Gaussian Mixture Models (GMM) Pedram Daee 3.11.2015 Outline Gaussian Mixture Models (GMM) Models Model families and parameters Parameter learning

More information

Modeling and Performance Analysis with Discrete-Event Simulation

Modeling and Performance Analysis with Discrete-Event Simulation Simulation Modeling and Performance Analysis with Discrete-Event Simulation Chapter 9 Input Modeling Contents Data Collection Identifying the Distribution with Data Parameter Estimation Goodness-of-Fit

More information

STA414/2104. Lecture 11: Gaussian Processes. Department of Statistics

STA414/2104. Lecture 11: Gaussian Processes. Department of Statistics STA414/2104 Lecture 11: Gaussian Processes Department of Statistics www.utstat.utoronto.ca Delivered by Mark Ebden with thanks to Russ Salakhutdinov Outline Gaussian Processes Exam review Course evaluations

More information

Stability and innovation of human activity spaces

Stability and innovation of human activity spaces Stability and innovation of human activity spaces http://www.ivt.ethz.ch/vpl/publications/reports/ab258.pdf Stefan Schönfelder * IVT - Institute for Transport Planning and Systems ETH - Swiss Federal Institute

More information

Spatial Pattern Analysis: Mapping Trends and Clusters

Spatial Pattern Analysis: Mapping Trends and Clusters Esri International User Conference San Diego, California Technical Workshops July 24, 2012 Spatial Pattern Analysis: Mapping Trends and Clusters Lauren M. Scott, PhD Lauren Rosenshein Bennett, MS Presentation

More information

PASSIVE MOBILE POSITIONING AS A WAY TO MAP THE CONNECTIONS BETWEEN CHANGE OF RESIDENCE AND DAILY MOBILITY: THE CASE OF ESTONIA

PASSIVE MOBILE POSITIONING AS A WAY TO MAP THE CONNECTIONS BETWEEN CHANGE OF RESIDENCE AND DAILY MOBILITY: THE CASE OF ESTONIA Pilleriine Kamenjuk, Anto Aasa University of Tartu, Department of Geography PASSIVE MOBILE POSITIONING AS A WAY TO MAP THE CONNECTIONS BETWEEN CHANGE OF RESIDENCE AND DAILY MOBILITY: THE CASE OF ESTONIA

More information

Unit 1, Lesson 2. What is geographic inquiry?

Unit 1, Lesson 2. What is geographic inquiry? What is geographic inquiry? Unit 1, Lesson 2 Understanding the way in which social scientists investigate problems will help you conduct your own investigations about problems or issues facing your community

More information

Mock Exam - 2 hours - use of basic (non-programmable) calculator is allowed - all exercises carry the same marks - exam is strictly individual

Mock Exam - 2 hours - use of basic (non-programmable) calculator is allowed - all exercises carry the same marks - exam is strictly individual Mock Exam - 2 hours - use of basic (non-programmable) calculator is allowed - all exercises carry the same marks - exam is strictly individual Question 1. Suppose you want to estimate the percentage of

More information

1. Write down the term 2. Write down the book definition 3. Put the definition in your own words 4. Draw an image and/or put a Real Life Example

1. Write down the term 2. Write down the book definition 3. Put the definition in your own words 4. Draw an image and/or put a Real Life Example Unit 1 Vocabulary 1. Write down the term 2. Write down the book definition 3. Put the definition in your own words 4. Draw an image and/or put a Real Life Example Absolute Location Where Is It EXACTLY?

More information

Activity Identification from GPS Trajectories Using Spatial Temporal POIs Attractiveness

Activity Identification from GPS Trajectories Using Spatial Temporal POIs Attractiveness Activity Identification from GPS Trajectories Using Spatial Temporal POIs Attractiveness Lian Huang, Qingquan Li, Yang Yue State Key Laboratory of Information Engineering in Survey, Mapping and Remote

More information

Using Crowdsourced Data in Location-based Social Networks to Explore Influence Maximization

Using Crowdsourced Data in Location-based Social Networks to Explore Influence Maximization Using Crowdsourced Data in Location-based Social Networks to Explore Influence Maximization Ji Li Zhipeng Cai Department of Computer Science Georgia State University Atlanta, Georgia 33 Email: jli3@student.gsu.edu

More information

SYSM 6303: Quantitative Introduction to Risk and Uncertainty in Business Lecture 4: Fitting Data to Distributions

SYSM 6303: Quantitative Introduction to Risk and Uncertainty in Business Lecture 4: Fitting Data to Distributions SYSM 6303: Quantitative Introduction to Risk and Uncertainty in Business Lecture 4: Fitting Data to Distributions M. Vidyasagar Cecil & Ida Green Chair The University of Texas at Dallas Email: M.Vidyasagar@utdallas.edu

More information

Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, Spis treści

Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, Spis treści Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, 2017 Spis treści Website Acknowledgments Notation xiii xv xix 1 Introduction 1 1.1 Who Should Read This Book?

More information

Cluster Analysis using SaTScan

Cluster Analysis using SaTScan Cluster Analysis using SaTScan Summary 1. Statistical methods for spatial epidemiology 2. Cluster Detection What is a cluster? Few issues 3. Spatial and spatio-temporal Scan Statistic Methods Probability

More information

Course Introduction and Overview Descriptive Statistics Conceptualizations of Variance Review of the General Linear Model

Course Introduction and Overview Descriptive Statistics Conceptualizations of Variance Review of the General Linear Model Course Introduction and Overview Descriptive Statistics Conceptualizations of Variance Review of the General Linear Model PSYC 943 (930): Fundamentals of Multivariate Modeling Lecture 1: August 22, 2012

More information

A few applications of the SVD

A few applications of the SVD A few applications of the SVD Many methods require to approximate the original data (matrix) by a low rank matrix before attempting to solve the original problem Regularization methods require the solution

More information

Glossary. The ISI glossary of statistical terms provides definitions in a number of different languages:

Glossary. The ISI glossary of statistical terms provides definitions in a number of different languages: Glossary The ISI glossary of statistical terms provides definitions in a number of different languages: http://isi.cbs.nl/glossary/index.htm Adjusted r 2 Adjusted R squared measures the proportion of the

More information

RaRE: Social Rank Regulated Large-scale Network Embedding

RaRE: Social Rank Regulated Large-scale Network Embedding RaRE: Social Rank Regulated Large-scale Network Embedding Authors: Yupeng Gu 1, Yizhou Sun 1, Yanen Li 2, Yang Yang 3 04/26/2018 The Web Conference, 2018 1 University of California, Los Angeles 2 Snapchat

More information

arxiv: v1 [physics.soc-ph] 20 Aug 2014

arxiv: v1 [physics.soc-ph] 20 Aug 2014 MEASURES OF HUMAN MOBILITY USING MOBILE PHONE RECORDS ENHANCED WITH GIS DATA NATHALIE E. WILLIAMS, TIMOTHY A. THOMAS, MATTHEW DUNBAR, NATHAN EAGLE, AND ADRIAN DOBRA arxiv:1408.5420v1 [physics.soc-ph] 20

More information

CSE 473: Artificial Intelligence Autumn Topics

CSE 473: Artificial Intelligence Autumn Topics CSE 473: Artificial Intelligence Autumn 2014 Bayesian Networks Learning II Dan Weld Slides adapted from Jack Breese, Dan Klein, Daphne Koller, Stuart Russell, Andrew Moore & Luke Zettlemoyer 1 473 Topics

More information

Understanding Social Characteristic from Spatial Proximity in Mobile Social Network

Understanding Social Characteristic from Spatial Proximity in Mobile Social Network INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL ISSN 1841-9836, 10(4):539-550, August, 2015. Understanding Social Characteristic from Spatial Proximity in Mobile Social Network D. Hu, B. Huang,

More information

Basics of Experimental Design. Review of Statistics. Basic Study. Experimental Design. When an Experiment is Not Possible. Studying Relations

Basics of Experimental Design. Review of Statistics. Basic Study. Experimental Design. When an Experiment is Not Possible. Studying Relations Basics of Experimental Design Review of Statistics And Experimental Design Scientists study relation between variables In the context of experiments these variables are called independent and dependent

More information

Data files for today. CourseEvalua2on2.sav pontokprediktorok.sav Happiness.sav Ca;erplot.sav

Data files for today. CourseEvalua2on2.sav pontokprediktorok.sav Happiness.sav Ca;erplot.sav Correlation Data files for today CourseEvalua2on2.sav pontokprediktorok.sav Happiness.sav Ca;erplot.sav Defining Correlation Co-variation or co-relation between two variables These variables change together

More information

Model Based Clustering of Count Processes Data

Model Based Clustering of Count Processes Data Model Based Clustering of Count Processes Data Tin Lok James Ng, Brendan Murphy Insight Centre for Data Analytics School of Mathematics and Statistics May 15, 2017 Tin Lok James Ng, Brendan Murphy (Insight)

More information

Harvard University. Rigorous Research in Engineering Education

Harvard University. Rigorous Research in Engineering Education Statistical Inference Kari Lock Harvard University Department of Statistics Rigorous Research in Engineering Education 12/3/09 Statistical Inference You have a sample and want to use the data collected

More information

Socio-Economic Levels and Human Mobility

Socio-Economic Levels and Human Mobility 1 Socio-Economic Levels and Human Mobility V. Frias-Martinez, J. Virseda, E. Frias-Martinez Abstract Socio-economic levels provide an understanding of the population s access to housing, education, health

More information

Assessing the Influence of Spatio-Temporal Context for Next Place Prediction using Different Machine Learning Approaches

Assessing the Influence of Spatio-Temporal Context for Next Place Prediction using Different Machine Learning Approaches International Journal of Geo-Information Article Assessing the Influence of Spatio-Temporal Context for Next Place Prediction using Different Machine Learning Approaches Jorim Urner 1 ID, Dominik Bucher

More information

K-Means and Gaussian Mixture Models

K-Means and Gaussian Mixture Models K-Means and Gaussian Mixture Models David Rosenberg New York University October 29, 2016 David Rosenberg (New York University) DS-GA 1003 October 29, 2016 1 / 42 K-Means Clustering K-Means Clustering David

More information

Personalized POI Recommendation on Location-Based Social Networks. Huiji Gao

Personalized POI Recommendation on Location-Based Social Networks. Huiji Gao Personalized POI Recommendation on Location-Based Social Networks by Huiji Gao A Dissertation Presented in Partial Fulfillment of the Requirement for the Degree Doctor of Philosophy Approved November 2014

More information

DYNAMIC TRIP ATTRACTION ESTIMATION WITH LOCATION BASED SOCIAL NETWORK DATA BALANCING BETWEEN TIME OF DAY VARIATIONS AND ZONAL DIFFERENCES

DYNAMIC TRIP ATTRACTION ESTIMATION WITH LOCATION BASED SOCIAL NETWORK DATA BALANCING BETWEEN TIME OF DAY VARIATIONS AND ZONAL DIFFERENCES DYNAMIC TRIP ATTRACTION ESTIMATION WITH LOCATION BASED SOCIAL NETWORK DATA BALANCING BETWEEN TIME OF DAY VARIATIONS AND ZONAL DIFFERENCES Nicholas W. Hu a, Peter J. Jin b, * a Department of Civil and Environmental

More information

Recommender systems, matrix factorization, variable selection and social graph data

Recommender systems, matrix factorization, variable selection and social graph data Recommender systems, matrix factorization, variable selection and social graph data Julien Delporte & Stéphane Canu stephane.canu@litislab.eu StatLearn, april 205, Grenoble Road map Model selection for

More information

Modeling population growth in online social networks

Modeling population growth in online social networks Zhu et al. Complex Adaptive Systems Modeling 3, :4 RESEARCH Open Access Modeling population growth in online social networks Konglin Zhu *,WenzhongLi, and Xiaoming Fu *Correspondence: zhu@cs.uni-goettingen.de

More information

Classification in Mobility Data Mining

Classification in Mobility Data Mining Classification in Mobility Data Mining Activity Recognition Semantic Enrichment Recognition through Points-of-Interest Given a dataset of GPS tracks of private vehicles, we annotate trajectories with the

More information

Recommendation Systems

Recommendation Systems Recommendation Systems Pawan Goyal CSE, IITKGP October 29-30, 2015 Pawan Goyal (IIT Kharagpur) Recommendation Systems October 29-30, 2015 1 / 61 Recommendation System? Pawan Goyal (IIT Kharagpur) Recommendation

More information