Collaborative Nowcasting for Contextual Recommendation

Size: px
Start display at page:

Download "Collaborative Nowcasting for Contextual Recommendation"

Transcription

1 Collaborative for Contextual Recommendation Yu Sun 1, Nicholas Jing Yuan 2, Xing Xie 3, Kieran McDonald 4, Rui Zhang 5 University of Melbourne { 1 sun.y, 5 rui.zhang}@unimelb.edu.au Microsoft Research Microsoft Corporation { 2 nicholas.yuan, 3 xing.xie, 4 kieran.mcdonald}@microsoft.com April 14 th 2016

2 Outline 1 Motivation and Problem Definition 2 3 4

3 Outline Motivation Problem Definition 1 Motivation and Problem Definition Motivation Problem Definition 2 3 Set-up Results 4

4 Motivation Problem Definition Proactive Experiences on Mobile Phones Digital assistants: Cortana, Google Now, Siri. Proactive experiences recommend the right information at just the right time a and help you get things done b even before you ask c. a b c

5 Motivation Problem Definition Proactive Experiences on Mobile Phones Information types: videos, news, traffic, weather, apps, places, (calendar, stock prices, sports) etc. Each type in such a layout is called a card

6 Motivation Problem Definition Proactive Experiences on Mobile Phones Limited display size = show one or two cards Which card a user needs = intent to have dinner = restaurant card to drive home = traffic card To recommend the right information at the right time, need monitor intent

7 Intent and Context Motivation Problem Definition Intent Context external context: physical environment (e.g., time, location) internal context: users states (e.g., activity, usage of apps) Example (From Context to Intent) context: 6:00 p.m., in the office intent: to drive home context: just left a shopping center, using Yelp intent: to find a restaurant

8 Intent and Context Motivation Problem Definition Relationship between context and intent is difficult to model intent and context change swiftly exhibit strong sequential correlation Context itself is heterogeneous and complicated all contemporaneous information related to the intent Challenge to model structure of context relationship between context and intent

9 Existing Work Motivation Problem Definition Traditional recommendation models cannot tackle the challenge only deal with a given intent (e.g., to find movies, books) recommend new items fulfilling the given intent Time-aware recommendation models also cannot apply do not consider other context besides time not suitable for swiftly changing context/intent Context-aware recommendation models do not work either do not take sequential correlation into account consider only external context (e.g., time, location)

10 Motivation Problem Definition New Recommendation Paradigm Personal Digital Assistant-Style Recommendation user-centered rather than product/item-centered recommendation based on multiple types of intent First step: monitoring real-time intent by context Wide Applications Proactive experiences Online advertisement

11 Outline Motivation Problem Definition 1 Motivation and Problem Definition Motivation Problem Definition 2 3 Set-up Results 4

12 Intent Monitoring Problem Motivation Problem Definition The studied problem is defined as follows: Definition (Intent Monitoring) Given a starting time t 0, a monitoring granularity, a type of intent γ and the context Xt u of user u, the intent monitoring problem is to predict whether user u has intent γ with context Xt u for each time step t of length starting from t 0. Example Time step 10 a.m. 11 a.m 12 p.m. 1 p.m. Now News intent ?

13 Outline 1 Motivation and Problem Definition Motivation Problem Definition 2 3 Set-up Results 4

14 Why? UW Engineering Bldg: Waterproofing went on one day 1 1 Picture from: Cliff Mass, University of Washington

15 Why? Washed off a few hours later 1 1 Picture from: Cliff Mass, University of Washington

16 Why? Reapplied the next day. How much did this cost? 1 1 Picture from: Cliff Mass, University of Washington

17 Difference between Nowcast and Forecast historical data side data historical data variable of interest variable of interest (a) Nowcast (b) Forecast Nowcast: prediction of current or very near future Difference: side data contemporaneous with more frequently available (e.g., industrial output GDP)

18 Side-Data Used in In meteorology: nowcasting weather atmospheric conditions from aircraft water vapor distributions from GPS receivers social media data from Facebook, Twitter, etc. In macroeconomics: nowcasting GDP personal consumption, industrial production surveys, financial variables (e.g., interest rates, CPI) Google trend data In data mining: nowcasting rainfall, illness rates search engine query log (e.g., Google trend) posts in social media (e.g., Twitter)

19 Existing Model Cannot Apply Thunderstorm: linear regression with exponential smoothing variable of interest quite different from intent GDP nowcasting: dynamic factor model granularity much larger than hours macroeconomic variables are non-personalized Rainfall nowcasting: Bootstrapped LASSO + regression cannot address the personalized scenario hard to obtain textual features for personalized intent

20 Outline 1 Motivation and Problem Definition Motivation Problem Definition 2 3 Set-up Results 4

21 The Panel Context stochastic processes Historical/side data time series All series for user u panel X u Time Step 10 a.m. 11 a.m 12 p.m. 1 p.m. Now Facebook Skype McDonald s IKEA Dist-to-Office Day-of-Week News Intent ?

22 Latent Factor Structure Latent Factors We assume that x i,t X has structure x i,t = λ i f t +ξ i,t, where f t = (f 1,t,.., f R,t ), λ i = (λ i,1,..,λ i,r ), and ξ i,t N(0, ψ 2 i,t ). Written in matrix form x t = Λf t +ξ t where x t = (x 1,t,.., x N,t ), Λ = (λ 1,..,λ N ), ξ t = (ξ 1,t,..,ξ N,t ) Factor Transition To exploit sequential pattern, we assume dynamics of latent factors have structure f t = Af t 1 + Bω t where A R R R, B R R Q, and ω t WN(0, I Q ).

23 Outline 1 Motivation and Problem Definition Motivation Problem Definition 2 3 Set-up Results 4

24 Estimation Overview User panel X u X Loading ˆΛ u F Collaborative latent factors For each u ˆΛ u F X u For each u ˆF u Personalized latent factors Intent s u Extracting Collaborative Latent Factors Kalman Filtering Regression Figure:

25 Collaborative Latent Factors: Using CP Decomposition M T w 1 w r N X v v r u 1 u r Estimation of Parameters After CP decomposition X u UD (u) V where D (u) = diag(w u,1,..., W u,r ), and U R N R, V R T R, W R M R. We have F = V and ˆΛ u = U u D (u).

26 Using PARAFAC2 Decomposition X u G u V L u Estimation of Parameters After PARAFAC2 decomposition X u G u HL u V where G u R Nu R, H R R R is invariant to u, L u R R R. We have F = V and ˆΛ u = G u HL u.

27 Personalized Latent Factors Time Update (Prediction) Collaborative latent factors are not sufficient static common structure unsuitable for personalized scenario Apply Kalman Filter on F u and X u ft = ˆf t 1 + ˆBω t P t = ˆP t 1  + ˆΨ t Measurement Update (Correction) K t = P t ˆΛ (ˆΛ P t ˆΛ + ˆΨ t ) 1 ˆft = f t + K t (x t ˆΛ f t ) ˆP t = (I K t ˆΛ) P t

28 Outline Set-up Results 1 Motivation and Problem Definition Motivation Problem Definition 2 3 Set-up Results 4

29 Data Sets Set-up Results Proactive log of a commercial digital assistant from June 10 th 2015 to July 9 th 2015 clicks as indicators of intent eight types of intent: news, weather, etc. in total contain 20,807 anonymous users Collect intent-related context, apps used and venues visited

30 Set-up Results Measurements and Compared Methods Measurements Macro F-measure: average performance among all users Micro F-measure: performance per instance Compared Methods BoostedTree: used in existing contextual ranking models FM: (factorization machine) for next-basket recommendation NowcastIndi: the macroeconomic nowcasting model CNowcastCP: CP decomp. for collaborative latent factors

31 Outline Set-up Results 1 Motivation and Problem Definition Motivation Problem Definition 2 3 Set-up Results 4

32 1 R 1 Q Motivation and Problem Definition Set-up Results Effect of Parameters R and Q 1.1 News Weather Finance Sports 1.1 News Weather Finance Sports RelativeMacroF-measure RelativeMacroF-measure Observation R = 4, Q = 2 is a good choice small performance variance

33 Set-up Results Comparison across Models Macro F-measure Model News Events Weather Places Finance Calendar Traffic Sports BoostedTree FM NowcastIndi CNowcastCP CNowcast Micro F-measure Model News Events Weather Places Finance Calendar Traffic Sports BoostedTree FM NowcastIndi CNowcastCP CNowcast

34 0 0 Motivation and Problem Definition Set-up Results Comparison across Monitoring Granularity PerformanceRatio MacroF-measure MicroF-measure MonitoringGranularity (h) (a) Ratio to BoostedTree PerformanceRatio MacroF-measure MicroF-measure MonitoringGranularity (h) (b) Ratio to FM Observation monitoring granularity ր performance advantage ր closer to now" suitable for nowcasting

35 Conclusion Contextual Intent Monitoring users real-time intent with context is key for personal digital assistant-style recommendation. The collaborative nowcasting model effectively models the complicated relationship between context and intent via nowcasting and collaborative capabilities.

Contextual Intent Tracking for Personal Assistants

Contextual Intent Tracking for Personal Assistants Contextual Intent Tracking for Personal Assistants Yu Sun 1, Nicholas Jing Yuan, Yingzi Wang 3, Xing Xie 4, Kieran McDonald 5, Rui Zhang 6 Department of Computing and Information Systems, University of

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

Nowcasting Norwegian GDP

Nowcasting Norwegian GDP Nowcasting Norwegian GDP Knut Are Aastveit and Tørres Trovik May 13, 2007 Introduction Motivation The last decades of advances in information technology has made it possible to access a huge amount of

More information

Chapter 7 Forecasting Demand

Chapter 7 Forecasting Demand Chapter 7 Forecasting Demand Aims of the Chapter After reading this chapter you should be able to do the following: discuss the role of forecasting in inventory management; review different approaches

More information

A Contextual Collaborative Approach for App Usage Forecasting

A Contextual Collaborative Approach for App Usage Forecasting A Contextual Collaborative Approach for App Usage Forecasting Yingzi Wang 1, Nicholas Jing Yuan 2, Yu Sun 3, Fuzheng Zhang 4, Xing Xie 5, Qi Liu 6, Enhong Chen 7 University of Science and Technology of

More information

Mobility Analytics through Social and Personal Data. Pierre Senellart

Mobility Analytics through Social and Personal Data. Pierre Senellart Mobility Analytics through Social and Personal Data Pierre Senellart Session: Big Data & Transport Business Convention on Big Data Université Paris-Saclay, 25 novembre 2015 Analyzing Transportation and

More information

Warwick Business School Forecasting System. Summary. Ana Galvao, Anthony Garratt and James Mitchell November, 2014

Warwick Business School Forecasting System. Summary. Ana Galvao, Anthony Garratt and James Mitchell November, 2014 Warwick Business School Forecasting System Summary Ana Galvao, Anthony Garratt and James Mitchell November, 21 The main objective of the Warwick Business School Forecasting System is to provide competitive

More information

Large-scale Information Processing, Summer Recommender Systems (part 2)

Large-scale Information Processing, Summer Recommender Systems (part 2) Large-scale Information Processing, Summer 2015 5 th Exercise Recommender Systems (part 2) Emmanouil Tzouridis tzouridis@kma.informatik.tu-darmstadt.de Knowledge Mining & Assessment SVM question When a

More information

Where to Find My Next Passenger?

Where to Find My Next Passenger? Where to Find My Next Passenger? Jing Yuan 1 Yu Zheng 2 Liuhang Zhang 1 Guangzhong Sun 1 1 University of Science and Technology of China 2 Microsoft Research Asia September 19, 2011 Jing Yuan et al. (USTC,MSRA)

More information

ELEC6910Q Analytics and Systems for Social Media and Big Data Applications Lecture 3 Centrality, Similarity, and Strength Ties

ELEC6910Q Analytics and Systems for Social Media and Big Data Applications Lecture 3 Centrality, Similarity, and Strength Ties ELEC6910Q Analytics and Systems for Social Media and Big Data Applications Lecture 3 Centrality, Similarity, and Strength Ties Prof. James She james.she@ust.hk 1 Last lecture 2 Selected works from Tutorial

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

Bayesian Contextual Multi-armed Bandits

Bayesian Contextual Multi-armed Bandits Bayesian Contextual Multi-armed Bandits Xiaoting Zhao Joint Work with Peter I. Frazier School of Operations Research and Information Engineering Cornell University October 22, 2012 1 / 33 Outline 1 Motivating

More information

Personalized Social Recommendations Accurate or Private

Personalized Social Recommendations Accurate or Private Personalized Social Recommendations Accurate or Private Presented by: Lurye Jenny Paper by: Ashwin Machanavajjhala, Aleksandra Korolova, Atish Das Sarma Outline Introduction Motivation The model General

More information

Predictive Discrete Latent Factor Models for large incomplete dyadic data

Predictive Discrete Latent Factor Models for large incomplete dyadic data Predictive Discrete Latent Factor Models for large incomplete dyadic data Deepak Agarwal, Srujana Merugu, Abhishek Agarwal Y! Research MMDS Workshop, Stanford University 6/25/2008 Agenda Motivating applications

More information

A look into the factor model black box Publication lags and the role of hard and soft data in forecasting GDP

A look into the factor model black box Publication lags and the role of hard and soft data in forecasting GDP A look into the factor model black box Publication lags and the role of hard and soft data in forecasting GDP Marta Bańbura and Gerhard Rünstler Directorate General Research European Central Bank November

More information

K-Nearest Neighbor Temporal Aggregate Queries

K-Nearest Neighbor Temporal Aggregate Queries Experiments and Conclusion K-Nearest Neighbor Temporal Aggregate Queries Yu Sun Jianzhong Qi Yu Zheng Rui Zhang Department of Computing and Information Systems University of Melbourne Microsoft Research,

More information

Introduction to Forecasting

Introduction to Forecasting Introduction to Forecasting Introduction to Forecasting Predicting the future Not an exact science but instead consists of a set of statistical tools and techniques that are supported by human judgment

More information

Cost and Preference in Recommender Systems Junhua Chen LESS IS MORE

Cost and Preference in Recommender Systems Junhua Chen LESS IS MORE Cost and Preference in Recommender Systems Junhua Chen, Big Data Research Center, UESTC Email:junmshao@uestc.edu.cn http://staff.uestc.edu.cn/shaojunming Abstract In many recommender systems (RS), user

More information

Collaborative Filtering

Collaborative Filtering Collaborative Filtering Nicholas Ruozzi University of Texas at Dallas based on the slides of Alex Smola & Narges Razavian Collaborative Filtering Combining information among collaborating entities to make

More information

Estimation of the Click Volume by Large Scale Regression Analysis May 15, / 50

Estimation of the Click Volume by Large Scale Regression Analysis May 15, / 50 Estimation of the Click Volume by Large Scale Regression Analysis Yuri Lifshits, Dirk Nowotka [International Computer Science Symposium in Russia 07, Ekaterinburg] Presented by: Aditya Menon UCSD May 15,

More information

PDF / LA CROSSE TECHNOLOGY WEATHER STATION RESET EBOOK

PDF / LA CROSSE TECHNOLOGY WEATHER STATION RESET EBOOK 06 March, 2018 PDF / LA CROSSE TECHNOLOGY WEATHER STATION RESET EBOOK Document Filetype: PDF 218.89 KB 0 PDF / LA CROSSE TECHNOLOGY WEATHER STATION RESET EBOOK Click here for factory reset. Animated weather

More information

SVAN 2016 Mini Course: Stochastic Convex Optimization Methods in Machine Learning

SVAN 2016 Mini Course: Stochastic Convex Optimization Methods in Machine Learning SVAN 2016 Mini Course: Stochastic Convex Optimization Methods in Machine Learning Mark Schmidt University of British Columbia, May 2016 www.cs.ubc.ca/~schmidtm/svan16 Some images from this lecture are

More information

Sequential Recommender Systems

Sequential Recommender Systems Recommender Stammtisch, Zalando, 26/6/14 Sequential Recommender Systems! Knowledge Mining & Assessment brefeld@kma.informatik.tu-darmstadt.de Collaborative Filtering Prof. Dr. 2 Collaborative Filtering

More information

Unified Modeling of User Activities on Social Networking Sites

Unified Modeling of User Activities on Social Networking Sites Unified Modeling of User Activities on Social Networking Sites Himabindu Lakkaraju IBM Research - India Manyata Embassy Business Park Bangalore, Karnataka - 5645 klakkara@in.ibm.com Angshu Rai IBM Research

More information

The Wind Hazard: Messaging the Wind Threat & Corresponding Potential Impacts

The Wind Hazard: Messaging the Wind Threat & Corresponding Potential Impacts The Wind Hazard: Messaging the Wind Threat & Corresponding Potential Impacts Scott Spratt Warning Coordination Meteorologist NWS Melbourne, FL David Sharp Science & Operations Officer NWS Melbourne, FL

More information

Collaborative Filtering. Radek Pelánek

Collaborative Filtering. Radek Pelánek Collaborative Filtering Radek Pelánek 2017 Notes on Lecture the most technical lecture of the course includes some scary looking math, but typically with intuitive interpretation use of standard machine

More information

Bayesian Variable Selection for Nowcasting Time Series

Bayesian Variable Selection for Nowcasting Time Series Bayesian Variable Selection for Time Series Steve Scott Hal Varian Google August 14, 2013 What day of the week are there the most searches for [hangover]? 1. Sunday 2. Monday 3. Tuesday 4. Wednesday 5.

More information

Climate Risk Visualization for Adaptation Planning and Emergency Response

Climate Risk Visualization for Adaptation Planning and Emergency Response Climate Risk Visualization for Adaptation Planning and Emergency Response NCR Flood Fact Finding Workshop Ricardo Saavedra ricardo@vizonomy.com Social Media, Mobile, and Big Data St. Peter s Basilica,

More information

WMO Guide on Integrated Urban Weather, Environment and Climate Services for Cities (IUWECS) Hong Kong- an experience from a high-density city

WMO Guide on Integrated Urban Weather, Environment and Climate Services for Cities (IUWECS) Hong Kong- an experience from a high-density city WMO Guide on Integrated Urban Weather, Environment and Climate Services for Cities (IUWECS) Hong Kong- an experience from a high-density city Dr. Chao REN Associate Professor School of Architecture The

More information

Nurture Nature Center Receives Grant From National Oceanic and Atmospheric Administration To Study Flood Forecast and Warning Tools

Nurture Nature Center Receives Grant From National Oceanic and Atmospheric Administration To Study Flood Forecast and Warning Tools Nurture Nature Center Receives Grant From National Oceanic and Atmospheric Administration To Study Flood Forecast and Warning Tools One of four national awards by National Weather Service to advance weather

More information

Mining Big Data Using Parsimonious Factor and Shrinkage Methods

Mining Big Data Using Parsimonious Factor and Shrinkage Methods Mining Big Data Using Parsimonious Factor and Shrinkage Methods Hyun Hak Kim 1 and Norman Swanson 2 1 Bank of Korea and 2 Rutgers University ECB Workshop on using Big Data for Forecasting and Statistics

More information

CS 277: Data Mining. Mining Web Link Structure. CS 277: Data Mining Lectures Analyzing Web Link Structure Padhraic Smyth, UC Irvine

CS 277: Data Mining. Mining Web Link Structure. CS 277: Data Mining Lectures Analyzing Web Link Structure Padhraic Smyth, UC Irvine CS 277: Data Mining Mining Web Link Structure Class Presentations In-class, Tuesday and Thursday next week 2-person teams: 6 minutes, up to 6 slides, 3 minutes/slides each person 1-person teams 4 minutes,

More information

Leverage Sparse Information in Predictive Modeling

Leverage Sparse Information in Predictive Modeling Leverage Sparse Information in Predictive Modeling Liang Xie Countrywide Home Loans, Countrywide Bank, FSB August 29, 2008 Abstract This paper examines an innovative method to leverage information from

More information

A Wavelet Neural Network Forecasting Model Based On ARIMA

A Wavelet Neural Network Forecasting Model Based On ARIMA A Wavelet Neural Network Forecasting Model Based On ARIMA Wang Bin*, Hao Wen-ning, Chen Gang, He Deng-chao, Feng Bo PLA University of Science &Technology Nanjing 210007, China e-mail:lgdwangbin@163.com

More information

Defining Normal Weather for Energy and Peak Normalization

Defining Normal Weather for Energy and Peak Normalization Itron White Paper Energy Forecasting Defining Normal Weather for Energy and Peak Normalization J. Stuart McMenamin, Ph.D Managing Director, Itron Forecasting 2008, Itron Inc. All rights reserved. 1 Introduction

More information

Forecasting: principles and practice. Rob J Hyndman 1.1 Introduction to Forecasting

Forecasting: principles and practice. Rob J Hyndman 1.1 Introduction to Forecasting Forecasting: principles and practice Rob J Hyndman 1.1 Introduction to Forecasting 1 Outline 1 Background 2 Case studies 3 The statistical forecasting perspective 4 What can we forecast? 2 Resources Slides

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

Advances in promotional modelling and analytics

Advances in promotional modelling and analytics Advances in promotional modelling and analytics High School of Economics St. Petersburg 25 May 2016 Nikolaos Kourentzes n.kourentzes@lancaster.ac.uk O u t l i n e 1. What is forecasting? 2. Forecasting,

More information

Information Retrieval and Organisation

Information Retrieval and Organisation Information Retrieval and Organisation Chapter 13 Text Classification and Naïve Bayes Dell Zhang Birkbeck, University of London Motivation Relevance Feedback revisited The user marks a number of documents

More information

ECON 427: ECONOMIC FORECASTING. Ch1. Getting started OTexts.org/fpp2/

ECON 427: ECONOMIC FORECASTING. Ch1. Getting started OTexts.org/fpp2/ ECON 427: ECONOMIC FORECASTING Ch1. Getting started OTexts.org/fpp2/ 1 Outline 1 What can we forecast? 2 Time series data 3 Some case studies 4 The statistical forecasting perspective 2 Forecasting is

More information

Charles Kuster Leadville, CO. Personal Overview

Charles Kuster Leadville, CO. Personal Overview Charles Kuster Leadville, CO Personal Overview Personal Overview Charles Kuster Leadville, CO OU to study meteorology Charles Kuster Leadville, CO Personal Overview OU to study meteorology Graduated in

More information

The Infinite Dial 2019

The Infinite Dial 2019 The Infinite Dial 2019 Study Overview The Infinite Dial is the longest-running survey of digital media consumer behavior in America The annual reports in this series have covered a wide range of digital

More information

DANIEL WILSON AND BEN CONKLIN. Integrating AI with Foundation Intelligence for Actionable Intelligence

DANIEL WILSON AND BEN CONKLIN. Integrating AI with Foundation Intelligence for Actionable Intelligence DANIEL WILSON AND BEN CONKLIN Integrating AI with Foundation Intelligence for Actionable Intelligence INTEGRATING AI WITH FOUNDATION INTELLIGENCE FOR ACTIONABLE INTELLIGENCE in an arms race for artificial

More information

How to shape future met-services: a seamless perspective

How to shape future met-services: a seamless perspective How to shape future met-services: a seamless perspective Paolo Ruti, Chief World Weather Research Division Sarah Jones, Chair Scientific Steering Committee Improving the skill big resources ECMWF s forecast

More information

How we use social media to communicate weather news

How we use social media to communicate weather news How we use social media to communicate weather news The editorial met-team at METNorway WGCEF 12.10.2017 Norwegian Meteorological Institute INSTAGRAM - SHARING PICTURES Weather photos, 2-3 times a week.

More information

Chapter 13: Forecasting

Chapter 13: Forecasting Chapter 13: Forecasting Assistant Prof. Abed Schokry Operations and Productions Management First Semester 2013-2014 Chapter 13: Learning Outcomes You should be able to: List the elements of a good forecast

More information

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

ScienceDirect. Defining Measures for Location Visiting Preference

ScienceDirect. Defining Measures for Location Visiting Preference Available online at www.sciencedirect.com ScienceDirect Procedia Computer Science 63 (2015 ) 142 147 6th International Conference on Emerging Ubiquitous Systems and Pervasive Networks, EUSPN-2015 Defining

More information

Kostas Triantafyllopoulos University of Sheffield. Motivation / algorithmic pairs trading. Model set-up Detection of local mean-reversion

Kostas Triantafyllopoulos University of Sheffield. Motivation / algorithmic pairs trading. Model set-up Detection of local mean-reversion Detecting Mean Reverted Patterns in Statistical Arbitrage Outline Kostas Triantafyllopoulos University of Sheffield Motivation / algorithmic pairs trading Model set-up Detection of local mean-reversion

More information

Case Study 1: Estimating Click Probabilities. Kakade Announcements: Project Proposals: due this Friday!

Case Study 1: Estimating Click Probabilities. Kakade Announcements: Project Proposals: due this Friday! Case Study 1: Estimating Click Probabilities Intro Logistic Regression Gradient Descent + SGD Machine Learning for Big Data CSE547/STAT548, University of Washington Sham Kakade April 4, 017 1 Announcements:

More information

Scaling Neighbourhood Methods

Scaling Neighbourhood Methods Quick Recap Scaling Neighbourhood Methods Collaborative Filtering m = #items n = #users Complexity : m * m * n Comparative Scale of Signals ~50 M users ~25 M items Explicit Ratings ~ O(1M) (1 per billion)

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

Factor models. May 11, 2012

Factor models. May 11, 2012 Factor models May 11, 2012 Factor Models Macro economists have a peculiar data situation: Many data series, but usually short samples How can we utilize all this information without running into degrees

More information

Trends, Helpouts and Hidden Gems: Additional Google Tools to Strengthen Your Brand

Trends, Helpouts and Hidden Gems: Additional Google Tools to Strengthen Your Brand Trends, Helpouts and Hidden Gems: Additional Google Tools to Strengthen Your Brand a bit about me Father, husband of Kathy, Milan and Savannah Head of Social Strategy at WCG, a W2O Company Adjunct Professor,

More information

Collaborative Topic Modeling for Recommending Scientific Articles

Collaborative Topic Modeling for Recommending Scientific Articles Collaborative Topic Modeling for Recommending Scientific Articles Chong Wang and David M. Blei Best student paper award at KDD 2011 Computer Science Department, Princeton University Presented by Tian Cao

More information

Nowcasting and Short-Term Forecasting of Russia GDP

Nowcasting and Short-Term Forecasting of Russia GDP Nowcasting and Short-Term Forecasting of Russia GDP Elena Deryugina Alexey Ponomarenko Aleksey Porshakov Andrey Sinyakov Bank of Russia 12 th ESCB Emerging Markets Workshop, Saariselka December 11, 2014

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

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

Prolonged Coastal Storm October 9 th -12 th, 2013

Prolonged Coastal Storm October 9 th -12 th, 2013 Prolonged Coastal Storm October 9 th -12 th, 2013 Prepared 400 PM EDT Tuesday, October 8th, 2013 Gary Szatkowski NOAA s NJ Forecast office http://www.erh.noaa.gov/phi/ Purpose of Briefing Briefing #1 for

More information

Interact with Strangers

Interact with Strangers Interact with Strangers RATE: Recommendation-aware Trust Evaluation in Online Social Networks Wenjun Jiang 1, 2, Jie Wu 2, and Guojun Wang 1 1. School of Information Science and Engineering, Central South

More information

NCDREC: A Decomposability Inspired Framework for Top-N Recommendation

NCDREC: A Decomposability Inspired Framework for Top-N Recommendation NCDREC: A Decomposability Inspired Framework for Top-N Recommendation Athanasios N. Nikolakopoulos,2 John D. Garofalakis,2 Computer Engineering and Informatics Department, University of Patras, Greece

More information

1. Shocks. This version: February 15, Nr. 1

1. Shocks. This version: February 15, Nr. 1 1. Shocks This version: February 15, 2006 Nr. 1 1.3. Factor models What if there are more shocks than variables in the VAR? What if there are only a few underlying shocks, explaining most of fluctuations?

More information

Micro-Randomized Trials & mhealth. S.A. Murphy NRC 8/2014

Micro-Randomized Trials & mhealth. S.A. Murphy NRC 8/2014 Micro-Randomized Trials & mhealth S.A. Murphy NRC 8/2014 mhealth Goal: Design a Continually Learning Mobile Health Intervention: HeartSteps + Designing a Micro-Randomized Trial 2 Data from wearable devices

More information

Sensor Tasking and Control

Sensor Tasking and Control Sensor Tasking and Control Sensing Networking Leonidas Guibas Stanford University Computation CS428 Sensor systems are about sensing, after all... System State Continuous and Discrete Variables The quantities

More information

Journal of Chemical and Pharmaceutical Research, 2014, 6(5): Research Article

Journal of Chemical and Pharmaceutical Research, 2014, 6(5): Research Article Available online www.jocpr.com Journal of Chemical and Pharmaceutical Research, 2014, 6(5):266-270 Research Article ISSN : 0975-7384 CODEN(USA) : JCPRC5 Anomaly detection of cigarette sales using ARIMA

More information

Title: Storm of the Century: Documenting the 1993 Superstorm

Title: Storm of the Century: Documenting the 1993 Superstorm A. PAIIF 2011 Cover Page Title: Storm of the Century: Documenting the 1993 Superstorm Point of Contact: Name: Alex Granger Email: alex.granger@noaa.gov Phone Number: 571-555-9278 Mailing Address: Research

More information

Smart Route Recommendations based on Historical GPS Trajectories and Weather Information

Smart Route Recommendations based on Historical GPS Trajectories and Weather Information Smart Route Recommendations based on Historical GPS Trajectories and Weather Information Xingzhe Xie1, Kevin Wong2, Hamid Aghajan2 and Wilfried Philips1 1 TELIN IPI iminds, Ghent University, Belgium 2

More information

Factor models. March 13, 2017

Factor models. March 13, 2017 Factor models March 13, 2017 Factor Models Macro economists have a peculiar data situation: Many data series, but usually short samples How can we utilize all this information without running into degrees

More information

Stat 406: Algorithms for classification and prediction. Lecture 1: Introduction. Kevin Murphy. Mon 7 January,

Stat 406: Algorithms for classification and prediction. Lecture 1: Introduction. Kevin Murphy. Mon 7 January, 1 Stat 406: Algorithms for classification and prediction Lecture 1: Introduction Kevin Murphy Mon 7 January, 2008 1 1 Slides last updated on January 7, 2008 Outline 2 Administrivia Some basic definitions.

More information

Factor Models for Asset Returns. Prof. Daniel P. Palomar

Factor Models for Asset Returns. Prof. Daniel P. Palomar Factor Models for Asset Returns Prof. Daniel P. Palomar The Hong Kong University of Science and Technology (HKUST) MAFS6010R- Portfolio Optimization with R MSc in Financial Mathematics Fall 2018-19, HKUST,

More information

Challenges in providing effective flood forecasts and warnings

Challenges in providing effective flood forecasts and warnings Challenges in providing effective flood forecasts and warnings National Centre for Flood Research Inaugural Symposium Justin Robinson Bureau of Meteorology October 2018 Zero Lives Lost A key responsibility

More information

MDSS Functional Prototype Display System Preview April 2002

MDSS Functional Prototype Display System Preview April 2002 MDSS Functional Prototype Display System Preview April 2002 Bill Mahoney National Center for Atmospheric Research Images shown are valid as of 15 April 2002 NCAR MDSS Display System - Overview The MDSS

More information

Recommendation Systems

Recommendation Systems Recommendation Systems Pawan Goyal CSE, IITKGP October 21, 2014 Pawan Goyal (IIT Kharagpur) Recommendation Systems October 21, 2014 1 / 52 Recommendation System? Pawan Goyal (IIT Kharagpur) Recommendation

More information

Chapter 4: Factor Analysis

Chapter 4: Factor Analysis Chapter 4: Factor Analysis In many studies, we may not be able to measure directly the variables of interest. We can merely collect data on other variables which may be related to the variables of interest.

More information

Decoupled Collaborative Ranking

Decoupled Collaborative Ranking Decoupled Collaborative Ranking Jun Hu, Ping Li April 24, 2017 Jun Hu, Ping Li WWW2017 April 24, 2017 1 / 36 Recommender Systems Recommendation system is an information filtering technique, which provides

More information

Geo-identification and pedestrian navigation with geo-mobile applications: how do users proceed?

Geo-identification and pedestrian navigation with geo-mobile applications: how do users proceed? TU Vienna presentation 17 th July 2008 Geo-identification and pedestrian navigation with geo-mobile applications: how do users proceed? Ioannis Delikostidis Corné van Elzakker INTERNATIONAL INSTITUTE FOR

More information

SYSTEM OPERATIONS. Dr. Frank A. Monforte

SYSTEM OPERATIONS. Dr. Frank A. Monforte SYSTEM OPERATIONS FORECASTING Dr. Frank A. Monforte Itron s Forecasting Brown Bag Seminar September 13, 2011 PLEASE REMEMBER» In order to help this session run smoothly, your phones are muted.» To make

More information

Chapter 8 - Forecasting

Chapter 8 - Forecasting Chapter 8 - Forecasting Operations Management by R. Dan Reid & Nada R. Sanders 4th Edition Wiley 2010 Wiley 2010 1 Learning Objectives Identify Principles of Forecasting Explain the steps in the forecasting

More information

W. Douglas Wewer 1,2 *, Michael J. Jenkins 1

W. Douglas Wewer 1,2 *, Michael J. Jenkins 1 A PRACTITIONER S PERSPECTIVE: PROVIDING TIMELY AND RELEVANT MOUNTAIN WEATHER INFORMATION TO AVALANCHE WORKERS AT SNOWBASIN, A SUN VALLEY RESORT AND THE FOREST SERVICE UTAH AVALANCHE CENTER W. Douglas Wewer

More information

APPLICATIONS OF MINING HETEROGENEOUS INFORMATION NETWORKS

APPLICATIONS OF MINING HETEROGENEOUS INFORMATION NETWORKS APPLICATIONS OF MINING HETEROGENEOUS INFORMATION NETWORKS Yizhou Sun College of Computer and Information Science Northeastern University yzsun@ccs.neu.edu July 25, 2015 Heterogeneous Information Networks

More information

UDOT Weather Program Traffic Operations Center

UDOT Weather Program Traffic Operations Center UDOT Weather Program Traffic Operations Center Presentation Goals You MUST account for weather in your Traffic Management program Provide you with information on proven tools and strategies You NEED a

More information

Large-scale Ordinal Collaborative Filtering

Large-scale Ordinal Collaborative Filtering Large-scale Ordinal Collaborative Filtering Ulrich Paquet, Blaise Thomson, and Ole Winther Microsoft Research Cambridge, University of Cambridge, Technical University of Denmark ulripa@microsoft.com,brmt2@cam.ac.uk,owi@imm.dtu.dk

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

Estimation of the Click Volume by Large Scale Regression Analysis

Estimation of the Click Volume by Large Scale Regression Analysis Estimation of the Click Volume by Large Scale Regression Analysis Yury Lifshits 1 and Dirk Nowotka 2 1 Steklov Institute of Mathematics St.Petersburg, Russia, yura@logic.pdmi.ras.ru 2 FMI, Universität

More information

ECE521 Lecture 19 HMM cont. Inference in HMM

ECE521 Lecture 19 HMM cont. Inference in HMM ECE521 Lecture 19 HMM cont. Inference in HMM Outline Hidden Markov models Model definitions and notations Inference in HMMs Learning in HMMs 2 Formally, a hidden Markov model defines a generative process

More information

SGA-2: WP6- Early estimates. SURS: Boro Nikić, Tomaž Špeh ESSnet Big Data Project Brussels 26.,

SGA-2: WP6- Early estimates. SURS: Boro Nikić, Tomaž Špeh ESSnet Big Data Project Brussels 26., SGA-2: WP6- Early estimates SURS: Boro Nikić, Tomaž Špeh ESSnet Big Data Project Brussels 26.,27.10. 2017 Outline WP6 state of affairs WP6 pilot: Early estimates of economic indicators Methods Data sources

More information

ARIES HOROSCOPE 2016 By Lisa Lazuli

ARIES HOROSCOPE 2016 By Lisa Lazuli ARIES HOROSCOPE 2016 By Lisa Lazuli If searched for a ebook by Lisa Lazuli ARIES HOROSCOPE 2016 in pdf format, in that case you come on to loyal website. We present the utter variation of this ebook in

More information

Hong Kong Observatory Summer Placement Programme 2017

Hong Kong Observatory Summer Placement Programme 2017 Hong Kong Observatory Summer Placement Programme 2017 Training Programme : supervise the student. A mentor from the Hong Kong Observatory with relevant expertise will Training Period : 8 weeks, starting

More information

IH 35 at Blanco River May 2015

IH 35 at Blanco River May 2015 IH 35 at Blanco River May 2015 Presentation Objectives Background of historical damage assessment processes Introduction to Collector App ( Mat Peck) Collector App and Flood Damage Assessment (Katie Steele)

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

Planner's Postcode Area Map (Route Planning Map)

Planner's Postcode Area Map (Route Planning Map) Planner's Postcode Area Map (Route Planning Map) If you are looking for a book Planner's Postcode Area Map (Route Planning Map) in pdf form, then you have come on to correct website. We presented utter

More information

NWS Resources For Public Works

NWS Resources For Public Works NWS Resources For Public Works August 28th, 2016 Shawn DeVinny shawn.devinny@noaa.gov Meteorologist National Weather Service Twin Cities/Chanhassen, MN 1 APWA 2016 PWX 8/28/2016 National Weather Service

More information

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

Friendship and Mobility: User Movement In Location-Based Social Networks. Eunjoon Cho* Seth A. Myers* Jure Leskovec Friendship and Mobility: User Movement In Location-Based Social Networks Eunjoon Cho* Seth A. Myers* Jure Leskovec Outline Introduction Related Work Data Observations from Data Model of Human Mobility

More information

Forecasting: Principles and Practice. Rob J Hyndman. 1. Introduction to forecasting OTexts.org/fpp/1/ OTexts.org/fpp/2/3

Forecasting: Principles and Practice. Rob J Hyndman. 1. Introduction to forecasting OTexts.org/fpp/1/ OTexts.org/fpp/2/3 Rob J Hyndman Forecasting: Principles and Practice 1. Introduction to forecasting OTexts.org/fpp/1/ OTexts.org/fpp/2/3 Forecasting: Principles and Practice 1 Resources Slides Exercises Textbook Useful

More information

Social Studies Grade 2 - Building a Society

Social Studies Grade 2 - Building a Society Social Studies Grade 2 - Building a Society Description The second grade curriculum provides students with a broad view of the political units around them, specifically their town, state, and country.

More information

The Ultimate Guide To Chatbots For Businesses ONLIM 2018

The Ultimate Guide To Chatbots For Businesses ONLIM 2018 The Ultimate Guide To Chatbots For Businesses O N L I M 2 0 1 8 Where We're At Today Y o u ve probably heard a lot a b o u t c h a t b o t s d u r i n g 2 0 1 7. The l a s t y e a r h a s s h o w n u s

More information

Manotumruksa, J., Macdonald, C. and Ounis, I. (2018) Contextual Attention Recurrent Architecture for Context-aware Venue Recommendation. In: 41st International ACM SIGIR Conference on Research and Development

More information

9) Time series econometrics

9) Time series econometrics 30C00200 Econometrics 9) Time series econometrics Timo Kuosmanen Professor Management Science http://nomepre.net/index.php/timokuosmanen 1 Macroeconomic data: GDP Inflation rate Examples of time series

More information

Statistical NLP for the Web

Statistical NLP for the Web Statistical NLP for the Web Neural Networks, Deep Belief Networks Sameer Maskey Week 8, October 24, 2012 *some slides from Andrew Rosenberg Announcements Please ask HW2 related questions in courseworks

More information

The Case of Japan. ESRI CEPREMAP Joint Workshop November 13, Bank of Japan

The Case of Japan. ESRI CEPREMAP Joint Workshop November 13, Bank of Japan New Monthly Estimation Approach for Nowcasting GDP Growth: The Case of Japan ESRI CEPREMAP Joint Workshop November 13, 2014 Naoko Hara Bank of Japan * Views expressed in this paper are those of the authors,

More information