collaborative nowcasting for contextual recommendation · 2016-05-02 · motivation and problem...
TRANSCRIPT
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Collaborative Nowcasting for Contextual
Recommendation
Yu Sun †‡1, Nicholas Jing Yuan ‡2, Xing Xie ‡3,
Kieran McDonald ∗4, Rui Zhang †5
† University of Melbourne{
1sun.y,
5rui.zhang}@unimelb.edu.au
‡ Microsoft Research ∗ Microsoft Corporation{
2nicholas.yuan,
3xing.xie,
4kieran.mcdonald}@microsoft.com
April 14th 2016
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Outline
1 Motivation and Problem Definition
2 Collaborative Nowcasting Model
3 Experiments
4 Conclusion and Future Work
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work Motivation Problem Definition
Outline
1 Motivation and Problem Definition
Motivation
Problem Definition
2 Collaborative Nowcasting Model
Nowcasting
Model Formulation
Parameter Estimation
3 Experiments
Set-up
Results
4 Conclusion and Future Work
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work 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.
ahttp://www.google.com/landing/now/bhttp://dev.windows.com/en-us/cortanachttp://www.apple.com/ios/whats-new/
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work 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
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work Motivation Problem Definition
Proactive Experiences on Mobile Phones
Limited display size =⇒ showone or two cards
Which card a user needs ⇐=
intent
to have dinner =⇒restaurant cardto drive home =⇒ trafficcard
To recommend “the right
information at the right time”,need monitor intent
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work Motivation Problem Definition
Intent and Context
Intent! Contextexternal 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 drivehome
context: just left a shopping center, using Yelp intent:to find a restaurant
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work Motivation Problem Definition
Intent and Context
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
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work Motivation Problem Definition
Existing Work
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)
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work 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
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work Motivation Problem Definition
Outline
1 Motivation and Problem Definition
Motivation
Problem Definition
2 Collaborative Nowcasting Model
Nowcasting
Model Formulation
Parameter Estimation
3 Experiments
Set-up
Results
4 Conclusion and Future Work
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work Motivation Problem Definition
Intent Monitoring Problem
The studied problem is defined as follows:
Definition (Intent Monitoring)
Given a starting time t0, a monitoring granularity ∆, a type of
intent γ and the context X ut
of user u, the intent monitoring
problem is to predict whether user u has intent γ with context
X ut
for each time step t of length ∆ starting from t0.
Example
Time step 10 a.m. 11 a.m 12 p.m. 1 p.m. Now
News intent 0 0 1 1 ?
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Nowcasting Model FormulationParameter Estimation
Outline
1 Motivation and Problem Definition
Motivation
Problem Definition
2 Collaborative Nowcasting Model
Nowcasting
Model Formulation
Parameter Estimation
3 Experiments
Set-up
Results
4 Conclusion and Future Work
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Nowcasting Model FormulationParameter Estimation
Why Nowcasting?
UW Engineering Bldg: Waterproofing went on one day1
1Picture from: Cliff Mass, University of Washington
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Nowcasting Model FormulationParameter Estimation
Why Nowcasting?
Washed off a few hours later1
1Picture from: Cliff Mass, University of Washington
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Nowcasting Model FormulationParameter Estimation
Why Nowcasting?
Reapplied the next day. How much did this cost?1
1Picture from: Cliff Mass, University of Washington
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Nowcasting Model FormulationParameter Estimation
Difference between Nowcast and Forecast
historical data
variable ofinterest
side data
(a) Nowcast
historical data
variable ofinterest
(b) Forecast
Nowcast: prediction of current or very near future
Difference: side data
contemporaneous withmore frequently available (e.g., industrial output → GDP)
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Nowcasting Model FormulationParameter Estimation
Side-Data Used in Nowcasting
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)
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Nowcasting Model FormulationParameter Estimation
Existing Nowcasting 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
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Nowcasting Model FormulationParameter Estimation
Outline
1 Motivation and Problem Definition
Motivation
Problem Definition
2 Collaborative Nowcasting Model
Nowcasting
Model Formulation
Parameter Estimation
3 Experiments
Set-up
Results
4 Conclusion and Future Work
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Nowcasting Model FormulationParameter Estimation
The Panel
Context 7→ stochastic processes
Historical/side data 7→ time series
All series for user u 7→ panel X u
Time Step 10 a.m. 11 a.m 12 p.m. 1 p.m. Now
Facebook 306 0 915 32 257
Skype 0 1853 0 0 -McDonald’s 0 1256 652 0 0
IKEA 0 0 0 532 1247
Dist-to-Office 10.4 8.3 9.1 21.3 -Day-of-Week 6 6 6 6 6
News Intent 0 0 1 1 ?
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Nowcasting Model FormulationParameter Estimation
Latent Factor Structure
Latent Factors
We assume that xi ,t ∈ X has structure xi ,t = λ′i· ft + ξi ,t , where
ft = (f1,t , .., fR,t )′, λi = (λi ,1, .., λi ,R)
′, and ξi ,t ∼ N (0, ψ2i ,t).
Written in matrix form
xt = Λft + ξt
where xt = (x1,t , .., xN,t )′, Λ = (λ1, ..,λN )
′, ξt = (ξ1,t , .., ξN,t )′
Factor Transition
To exploit sequential pattern, we assume dynamics of latent
factors have structure
ft = Aft−1 + Bωt
where A ∈ RR×R, B ∈ R
R×Q, and ωt ∼ WN(0, IQ).
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Nowcasting Model FormulationParameter Estimation
Outline
1 Motivation and Problem Definition
Motivation
Problem Definition
2 Collaborative Nowcasting Model
Nowcasting
Model Formulation
Parameter Estimation
3 Experiments
Set-up
Results
4 Conclusion and Future Work
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Nowcasting Model FormulationParameter Estimation
Estimation Overview
Xu
User panel
X
Λu F
Loading
Collaborativelatent factors
Λu F
Xu
For each u
Fu
Personalizedlatent factors
For each u
su
Intent
Extracting Collaborative Latent Factors Kalman Filtering Regression
Figure: Collaborative Nowcasting Model
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Nowcasting Model FormulationParameter Estimation
Collaborative Latent Factors: Using CP Decomposition
XN
MT
u1 ur
v1 vr
w1 wr
≈ + · · · +
Estimation of Parameters
After CP decomposition
Xu ≈ UD
(u)V
′
where D(u) = diag(Wu,1, . . . ,Wu,r ), and U ∈ RN×R, V ∈ R
T×R,
W ∈ RM×R. We have
F = V′ and Λ
u = UuD
(u).
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Nowcasting Model FormulationParameter Estimation
Using PARAFAC2 Decomposition
X u V ′Gu
Lu
≈
Estimation of Parameters
After PARAFAC2 decomposition
Xu≈ G
uHL
uV
′
where Gu ∈ RNu×R , H ∈ R
R×R is invariant to u, Lu ∈ RR×R.
We have
F = V′ and Λ
u = GuHL
u.
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Nowcasting Model FormulationParameter Estimation
Personalized Latent Factors
Collaborative latent factors arenot sufficient
static common structureunsuitable forpersonalized scenario
Apply Kalman Filter on F u andX u
Time Update (Prediction)
ft = Aft−1 + Bωt
Pt = APt−1A′ + Ψt
Measurement Update
(Correction)
Kt = PtΛ′(ΛPtΛ
′+Ψt)−1
ft = ft + Kt(xt − Λft)Pt = (I − KtΛ)Pt
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work Set-up Results
Outline
1 Motivation and Problem Definition
Motivation
Problem Definition
2 Collaborative Nowcasting Model
Nowcasting
Model Formulation
Parameter Estimation
3 Experiments
Set-up
Results
4 Conclusion and Future Work
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work Set-up Results
Data Sets
Proactive log of a commercial digital assistant from
June 10th 2015 to July 9th 2015
clicks as indicators of intenteight types of intent: news, weather, etc.in total contain 20,807 anonymous users
Collect intent-related context, apps used and venuesvisited
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work 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
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work Set-up Results
Outline
1 Motivation and Problem Definition
Motivation
Problem Definition
2 Collaborative Nowcasting Model
Nowcasting
Model Formulation
Parameter Estimation
3 Experiments
Set-up
Results
4 Conclusion and Future Work
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work Set-up Results
Effect of Parameters R and Q
0.9
0.95
1
1.05
1.1
2 3 4 5 6
Relative Macro F-measure
R
News
Weather
Finance
Sports
0.9
0.95
1
1.05
1.1
1 2 3
Relative Macro F-measure
Q
News
Weather
Finance
Sports
Observation
R = 4, Q = 2 is a good choice
small performance variance
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work Set-up Results
Comparison across Models
Macro F-measure
Model News Events Weather Places Finance Calendar Traffic Sports
BoostedTree 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000
FM 0.877 1.102 1.459 3.465 1.263 9.179 1.332 1.395
NowcastIndi 1.746 2.643 4.403 12.70 3.788 14.92 5.800 4.221
CNowcastCP 1.766 2.513 4.329 12.16 3.412 15.33 5.483 4.195
CNowcast 1.963 2.950 4.904 14.13 4.680 16.95 7.377 5.264
Micro F-measure
Model News Events Weather Places Finance Calendar Traffic Sports
BoostedTree 1.000 1.000 1.000 1.000 1.000 1.000 1.000 1.000
FM 1.040 1.280 1.497 4.951 0.932 7.231 1.114 1.276
NowcastIndi 1.365 1.733 2.223 8.073 1.526 8.019 1.997 1.625
CNowcastCP 1.422 1.686 2.301 7.893 1.427 8.447 2.048 1.636
CNowcast 1.513 1.927 2.432 9.026 1.822 8.888 2.572 2.037
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work Set-up Results
Comparison across Monitoring Granularity
0
2
4
6
8
10
12
14
16
4 3 2 1
Performance Ratio
Monitoring Granularity (h)
Macro F-measure
Micro F-measure
(a) Ratio to BoostedTree
0
2
4
6
8
10
12
14
16
4 3 2 1
Performance Ratio
Monitoring Granularity (h)
Macro F-measure
Micro F-measure
(b) Ratio to FM
Observation
monitoring granularity ր ⇒ performance advantage ր
closer to “now" ⇒ suitable for nowcasting
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation
Motivation and Problem DefinitionCollaborative Nowcasting Model
ExperimentsConclusion and Future Work
Conclusion
Contextual Intent Monitoring
Nowcasting users’ real-time intent with context is key for
personal digital assistant-style recommendation.
Collaborative Nowcasting Model
The collaborative nowcasting model effectively models the
complicated relationship between context and intent via
nowcasting and collaborative capabilities.
Y. Sun, N. J. Yuan, X. Xie, K. McDonald and R. Zhang Collaborative Nowcasting for Contextual Recommendation