SlideShare a Scribd company logo
Differential Context
                         Relaxation for
                         Context-Aware
                         Travel
                         Recomendation
Yong Zheng, Robin Burke, Bamshad Mobasher
Center for Web Intelligence
DePaul University
Recommender System
 Any system that guides the user in a
  personalized way to interesting or useful
  objects in a large space of possible
  options or that produces such objects as
  output.
 Context-aware recommendation
  means that our definition of “useful”
   includes contextual considerations
Normal Recommendation




           Profile
 Restaurant1         Rating1

 Restaurant2         Rating2

     ...               ...
Context-Aware
Recommendation




                Profile
  Restaurant1   Rating1   Context1

  Restaurant2   Rating2   Context2
Approaches to CARS
 Filtering
   discard all options not appropriate to context
   (either before or after)

 Modeling
   build context into recommendation model

 Critical question
   What contextual features matter?

 The more context features we use
   The more options are filtered out
   The sparser the modeling space
Context as constraints
 We can view context-aware recommendation
  as imposing additional constraints on
  recommendation
  Options must be suitable to the context

 But we may be willing to relax these constraints to
  find nearby options
Relaxation




             etc.
Context matching
 Assume we have a set of contextual features c
  c = < f1, f2, f3, ... fn >

 Define a set of constraints, C

 Two contexts c and d match relative to
  constraints C iff
  Each feature in c and d matches relative to the
   corresponding constraint in C
Example: Hotel Ratings
 { trip type, days stayed, origin city, destination
  city, month of departure }

 c1 = {business, 3, Los Angeles, Chicago, July}

 c2 = {business, 7, Seattle, Chicago, January}

 Should they match or not?
Matching with constraints
 Two contexts
   c1 = {business, 3, Los Angeles, Chicago, July}
   c2 = {business, 7, Seattle, Chicago, January}

 Cstrict = { (exact trip type), (exact duration), (exact origin),
  (exact destination), (exact month) }
   no match

 Crelaxed = { (exact trip type), (any duration), (contained
  time_zone origin), (exact destination), (any month) }
   now the two contexts match

 If we are predicting for a user in context c2,
   we would not use a rating with context c1, if we apply
    constraint Cstrict
   we would use it, if we apply Crelaxed
Differential Context Relaxation
 The idea is to apply context to different
  components of a recommendation algorithm

 Rather than applying it in a uniform way

 Example
  kNN collaborative recommendation via Resnick’s
   algorithm



        Pred(u , i )  ru   
                                 vN
                                        wv  (rv ,i  rv )
                                        w
                                        vN
                                               v
Component 1: Neighbors
 Original algorithm
  Select neighbors who have rated item i

 Context-aware
  given context c
  Select neighbors who have rated item i in context
   matching c, relative to constraint C1



     Pred(u, i, c)  r 
                                vN
                                       wv  (rv,i  rv )
                         u
                                       w     v
                                       vN
Component 2: Peer Baseline
 Original algorithm
  Average over all of the ratings by a neighbor to
   establish a baseline

 Context-aware
  given context C
  Average over only those ratings matching c given
   constraint C2



      Pred(u, i, c)  r 
                                 vN
                                        wv  (rv,i  rv )
                          u
                                        w     v
                                        vN
Component 3: User baseline
 Original algorithm
  Average over all of the target user’s ratings to
   establish a baseline

 Context-aware
  given context C
  Average over the target users ratings given in
   contexts that match c, relative to constraint C3



      Pred(u, i, c)  r 
                                   vN
                                          wv  (rv,i  rv )
                           u
                                          w     v
                                          vN
Question
 How to choose C1, C2, C3 to make best use of the
  context information

 In other words
  what is the optimum relaxation of the contextual
   constraint
  applied differentially to each algorithm component?
Data set
 Tripadvisor

 Top 50 US cities

 2,562 users

 1,455 hotels

 9,251 ratings

 Fairly difficult recommendation task
  some work using “Trip Type” as a contextual variable
Context-linked features
 We decided to use user location and hotel location
  as context features
 Strictly speaking
   demographic
   content

 However research in the travel domain (Klenosky
  and Gitelson, 1998) shows these factors influence
  user’s expectations
   different standards for a California hotel vs a Nevada
    one
   behave like contextual features

 We call these “context-linked” features
Feature space
 trip type – solo, family, business, etc.

 origin city
   contained state
   contained time zone

 destination city
   contained state
   contained time zone

 Total of 32 possibilities
Optimization
 32 feature possibilities
 3 components
 323 = 32k possible constraint combinations
 But possible to eliminate some possibilities
 Example
   when averaging over a given user’s ratings
   user location is irrelevant
     will not filter anything out

 Able to shrink to < 400 combinations
   enough for exhaustive search
Results
Optimal constraints
Sensitivity
Differential Context
Relaxation
 Lets us incorporate context
   While managing the tradeoff between accuracy and coverage

 Future considerations
     other algorithms
     F1 optimization constraint
     instead of binary matching, real-valued?
     instead of selection, weighting of features?
     scalable optimization

 Stay tuned!
   RecSys CARS workshop
  Yong Zheng, Robin Burke, Bamshad Mobasher. "Optimal Feature Selection for Context-Aware
  Recommendation using Differential Relaxation". Proceedings of the 4th International Workshop
  on Context-Aware Recommender Systems (CARS 2012) held in conjunction with the 6th ACM
  Conference on Recommender Systems (RecSys 2012), Dublin, Ireland, Sep 2012
Questions

More Related Content

What's hot

[UMAP 2015] Integrating Context Similarity with Sparse Linear Recommendation ...
[UMAP 2015] Integrating Context Similarity with Sparse Linear Recommendation ...[UMAP 2015] Integrating Context Similarity with Sparse Linear Recommendation ...
[UMAP 2015] Integrating Context Similarity with Sparse Linear Recommendation ...
YONG ZHENG
 
[SAC 2015] Improve General Contextual SLIM Recommendation Algorithms By Facto...
[SAC 2015] Improve General Contextual SLIM Recommendation Algorithms By Facto...[SAC 2015] Improve General Contextual SLIM Recommendation Algorithms By Facto...
[SAC 2015] Improve General Contextual SLIM Recommendation Algorithms By Facto...
YONG ZHENG
 
Recsys 2016: Modeling Contextual Information in Session-Aware Recommender Sys...
Recsys 2016: Modeling Contextual Information in Session-Aware Recommender Sys...Recsys 2016: Modeling Contextual Information in Session-Aware Recommender Sys...
Recsys 2016: Modeling Contextual Information in Session-Aware Recommender Sys...
Bartlomiej Twardowski
 
Recommendation system
Recommendation systemRecommendation system
Recommendation system
Ding Li
 
Slope one recommender on hadoop
Slope one recommender on hadoopSlope one recommender on hadoop
Slope one recommender on hadoop
YONG ZHENG
 
Naver learning to rank question answer pairs using hrde-ltc
Naver learning to rank question answer pairs using hrde-ltcNaver learning to rank question answer pairs using hrde-ltc
Naver learning to rank question answer pairs using hrde-ltc
NAVER Engineering
 
lecture_mooney.ppt
lecture_mooney.pptlecture_mooney.ppt
lecture_mooney.pptbutest
 
Instance based learning
Instance based learningInstance based learning
Instance based learning
swapnac12
 
Cs583 recommender-systems
Cs583 recommender-systemsCs583 recommender-systems
Cs583 recommender-systems
Aravindharamanan S
 
3.1 clustering
3.1 clustering3.1 clustering
3.1 clustering
Krish_ver2
 
Clustering
ClusteringClustering
Clustering
NLPseminar
 
K means clustering
K means clusteringK means clustering
K means clustering
keshav goyal
 
Genetic algorithms
Genetic algorithmsGenetic algorithms
Genetic algorithms
swapnac12
 
Instance Based Learning in Machine Learning
Instance Based Learning in Machine LearningInstance Based Learning in Machine Learning
Instance Based Learning in Machine Learning
Pavithra Thippanaik
 
AI: Belief Networks
AI: Belief NetworksAI: Belief Networks
AI: Belief Networks
DataminingTools Inc
 
Investigating the Performance of Distanced-Based Weighted-Voting approaches i...
Investigating the Performance of Distanced-Based Weighted-Voting approaches i...Investigating the Performance of Distanced-Based Weighted-Voting approaches i...
Investigating the Performance of Distanced-Based Weighted-Voting approaches i...Dario Panada
 
Chapter 11 cluster advanced : web and text mining
Chapter 11 cluster advanced : web and text miningChapter 11 cluster advanced : web and text mining
Chapter 11 cluster advanced : web and text mining
Houw Liong The
 
Toward wave net speech synthesis
Toward wave net speech synthesisToward wave net speech synthesis
Toward wave net speech synthesis
NAVER Engineering
 
K-MEDOIDS CLUSTERING USING PARTITIONING AROUND MEDOIDS FOR PERFORMING FACE R...
K-MEDOIDS CLUSTERING  USING PARTITIONING AROUND MEDOIDS FOR PERFORMING FACE R...K-MEDOIDS CLUSTERING  USING PARTITIONING AROUND MEDOIDS FOR PERFORMING FACE R...
K-MEDOIDS CLUSTERING USING PARTITIONING AROUND MEDOIDS FOR PERFORMING FACE R...
ijscmc
 
Types of Machine Learnig Algorithms(CART, ID3)
Types of Machine Learnig Algorithms(CART, ID3)Types of Machine Learnig Algorithms(CART, ID3)
Types of Machine Learnig Algorithms(CART, ID3)
Fatimakhan325
 

What's hot (20)

[UMAP 2015] Integrating Context Similarity with Sparse Linear Recommendation ...
[UMAP 2015] Integrating Context Similarity with Sparse Linear Recommendation ...[UMAP 2015] Integrating Context Similarity with Sparse Linear Recommendation ...
[UMAP 2015] Integrating Context Similarity with Sparse Linear Recommendation ...
 
[SAC 2015] Improve General Contextual SLIM Recommendation Algorithms By Facto...
[SAC 2015] Improve General Contextual SLIM Recommendation Algorithms By Facto...[SAC 2015] Improve General Contextual SLIM Recommendation Algorithms By Facto...
[SAC 2015] Improve General Contextual SLIM Recommendation Algorithms By Facto...
 
Recsys 2016: Modeling Contextual Information in Session-Aware Recommender Sys...
Recsys 2016: Modeling Contextual Information in Session-Aware Recommender Sys...Recsys 2016: Modeling Contextual Information in Session-Aware Recommender Sys...
Recsys 2016: Modeling Contextual Information in Session-Aware Recommender Sys...
 
Recommendation system
Recommendation systemRecommendation system
Recommendation system
 
Slope one recommender on hadoop
Slope one recommender on hadoopSlope one recommender on hadoop
Slope one recommender on hadoop
 
Naver learning to rank question answer pairs using hrde-ltc
Naver learning to rank question answer pairs using hrde-ltcNaver learning to rank question answer pairs using hrde-ltc
Naver learning to rank question answer pairs using hrde-ltc
 
lecture_mooney.ppt
lecture_mooney.pptlecture_mooney.ppt
lecture_mooney.ppt
 
Instance based learning
Instance based learningInstance based learning
Instance based learning
 
Cs583 recommender-systems
Cs583 recommender-systemsCs583 recommender-systems
Cs583 recommender-systems
 
3.1 clustering
3.1 clustering3.1 clustering
3.1 clustering
 
Clustering
ClusteringClustering
Clustering
 
K means clustering
K means clusteringK means clustering
K means clustering
 
Genetic algorithms
Genetic algorithmsGenetic algorithms
Genetic algorithms
 
Instance Based Learning in Machine Learning
Instance Based Learning in Machine LearningInstance Based Learning in Machine Learning
Instance Based Learning in Machine Learning
 
AI: Belief Networks
AI: Belief NetworksAI: Belief Networks
AI: Belief Networks
 
Investigating the Performance of Distanced-Based Weighted-Voting approaches i...
Investigating the Performance of Distanced-Based Weighted-Voting approaches i...Investigating the Performance of Distanced-Based Weighted-Voting approaches i...
Investigating the Performance of Distanced-Based Weighted-Voting approaches i...
 
Chapter 11 cluster advanced : web and text mining
Chapter 11 cluster advanced : web and text miningChapter 11 cluster advanced : web and text mining
Chapter 11 cluster advanced : web and text mining
 
Toward wave net speech synthesis
Toward wave net speech synthesisToward wave net speech synthesis
Toward wave net speech synthesis
 
K-MEDOIDS CLUSTERING USING PARTITIONING AROUND MEDOIDS FOR PERFORMING FACE R...
K-MEDOIDS CLUSTERING  USING PARTITIONING AROUND MEDOIDS FOR PERFORMING FACE R...K-MEDOIDS CLUSTERING  USING PARTITIONING AROUND MEDOIDS FOR PERFORMING FACE R...
K-MEDOIDS CLUSTERING USING PARTITIONING AROUND MEDOIDS FOR PERFORMING FACE R...
 
Types of Machine Learnig Algorithms(CART, ID3)
Types of Machine Learnig Algorithms(CART, ID3)Types of Machine Learnig Algorithms(CART, ID3)
Types of Machine Learnig Algorithms(CART, ID3)
 

Viewers also liked

Lars an efficient and scalable location-aware recommender system
Lars  an efficient and scalable location-aware recommender systemLars  an efficient and scalable location-aware recommender system
Lars an efficient and scalable location-aware recommender system
Papitha Velumani
 
Lars an efficient and scalable location-aware recommender system
Lars  an efficient and scalable location-aware recommender systemLars  an efficient and scalable location-aware recommender system
Lars an efficient and scalable location-aware recommender system
Papitha Velumani
 
[논문발표] 20160801 A Sentiment-Enhanced Personalized Location Recommendation System
[논문발표] 20160801 A Sentiment-Enhanced Personalized Location Recommendation System[논문발표] 20160801 A Sentiment-Enhanced Personalized Location Recommendation System
[논문발표] 20160801 A Sentiment-Enhanced Personalized Location Recommendation System
Sanghoon Yoon
 
Travel route reconmmendations using geotagged photos
Travel route reconmmendations using geotagged photosTravel route reconmmendations using geotagged photos
Travel route reconmmendations using geotagged photosEli Boyarski
 
TTC16: Gadi Bashvitz - Travel Booking. Personalized
TTC16: Gadi Bashvitz - Travel Booking. Personalized TTC16: Gadi Bashvitz - Travel Booking. Personalized
TTC16: Gadi Bashvitz - Travel Booking. Personalized
Maksim Izmaylov
 
A cocktail approach for travel package recommendation
A cocktail approach for travel package recommendationA cocktail approach for travel package recommendation
A cocktail approach for travel package recommendation
Papitha Velumani
 
Peopleviews: Human Computation for Constraint-Based Recommendation
Peopleviews: Human Computation for Constraint-Based RecommendationPeopleviews: Human Computation for Constraint-Based Recommendation
Peopleviews: Human Computation for Constraint-Based Recommendation
Thomas Ulz
 
Applications of Machine Learning to Location-based Social Networks
Applications of Machine Learning to Location-based Social NetworksApplications of Machine Learning to Location-based Social Networks
Applications of Machine Learning to Location-based Social Networks
Joan Capdevila Pujol
 
REAL-TIME RECOMMENDATION SYSTEMS
REAL-TIME RECOMMENDATION SYSTEMS REAL-TIME RECOMMENDATION SYSTEMS
REAL-TIME RECOMMENDATION SYSTEMS
BigDataCloud
 
BIS4995 : Web-based Package Tour Reservation System
BIS4995 : Web-based Package Tour Reservation System BIS4995 : Web-based Package Tour Reservation System
BIS4995 : Web-based Package Tour Reservation System
Woraphan Atikomtrirat
 
Survey of Recommendation Systems
Survey of Recommendation SystemsSurvey of Recommendation Systems
Survey of Recommendation Systemsyoualab
 
Constraint based animation system
Constraint based animation systemConstraint based animation system
Constraint based animation system
Toru Hisai
 
A cocktail approach for travel package recommendation
A cocktail approach for travel package recommendationA cocktail approach for travel package recommendation
A cocktail approach for travel package recommendation
Papitha Velumani
 

Viewers also liked (13)

Lars an efficient and scalable location-aware recommender system
Lars  an efficient and scalable location-aware recommender systemLars  an efficient and scalable location-aware recommender system
Lars an efficient and scalable location-aware recommender system
 
Lars an efficient and scalable location-aware recommender system
Lars  an efficient and scalable location-aware recommender systemLars  an efficient and scalable location-aware recommender system
Lars an efficient and scalable location-aware recommender system
 
[논문발표] 20160801 A Sentiment-Enhanced Personalized Location Recommendation System
[논문발표] 20160801 A Sentiment-Enhanced Personalized Location Recommendation System[논문발표] 20160801 A Sentiment-Enhanced Personalized Location Recommendation System
[논문발표] 20160801 A Sentiment-Enhanced Personalized Location Recommendation System
 
Travel route reconmmendations using geotagged photos
Travel route reconmmendations using geotagged photosTravel route reconmmendations using geotagged photos
Travel route reconmmendations using geotagged photos
 
TTC16: Gadi Bashvitz - Travel Booking. Personalized
TTC16: Gadi Bashvitz - Travel Booking. Personalized TTC16: Gadi Bashvitz - Travel Booking. Personalized
TTC16: Gadi Bashvitz - Travel Booking. Personalized
 
A cocktail approach for travel package recommendation
A cocktail approach for travel package recommendationA cocktail approach for travel package recommendation
A cocktail approach for travel package recommendation
 
Peopleviews: Human Computation for Constraint-Based Recommendation
Peopleviews: Human Computation for Constraint-Based RecommendationPeopleviews: Human Computation for Constraint-Based Recommendation
Peopleviews: Human Computation for Constraint-Based Recommendation
 
Applications of Machine Learning to Location-based Social Networks
Applications of Machine Learning to Location-based Social NetworksApplications of Machine Learning to Location-based Social Networks
Applications of Machine Learning to Location-based Social Networks
 
REAL-TIME RECOMMENDATION SYSTEMS
REAL-TIME RECOMMENDATION SYSTEMS REAL-TIME RECOMMENDATION SYSTEMS
REAL-TIME RECOMMENDATION SYSTEMS
 
BIS4995 : Web-based Package Tour Reservation System
BIS4995 : Web-based Package Tour Reservation System BIS4995 : Web-based Package Tour Reservation System
BIS4995 : Web-based Package Tour Reservation System
 
Survey of Recommendation Systems
Survey of Recommendation SystemsSurvey of Recommendation Systems
Survey of Recommendation Systems
 
Constraint based animation system
Constraint based animation systemConstraint based animation system
Constraint based animation system
 
A cocktail approach for travel package recommendation
A cocktail approach for travel package recommendationA cocktail approach for travel package recommendation
A cocktail approach for travel package recommendation
 

Similar to [ECWEB2012]Differential Context Relaxation for Context-Aware Travel Recommendation

CARR’13 - Semantically-Enhanced Pre-Filtering for CARS
CARR’13 - Semantically-Enhanced Pre-Filtering for CARSCARR’13 - Semantically-Enhanced Pre-Filtering for CARS
CARR’13 - Semantically-Enhanced Pre-Filtering for CARSVictor Codina
 
Download
DownloadDownload
Downloadbutest
 
Download
DownloadDownload
Downloadbutest
 
Transferring Semantic Categories with Vertex Kernels: Recommendations with Se...
Transferring Semantic Categories with Vertex Kernels: Recommendations with Se...Transferring Semantic Categories with Vertex Kernels: Recommendations with Se...
Transferring Semantic Categories with Vertex Kernels: Recommendations with Se...
Matthew Rowe
 
LCBM: Statistics-Based Parallel Collaborative Filtering
LCBM: Statistics-Based Parallel Collaborative FilteringLCBM: Statistics-Based Parallel Collaborative Filtering
LCBM: Statistics-Based Parallel Collaborative Filtering
Fabio Petroni, PhD
 
Extending Recommendation Systems With Semantics And Context Awareness
Extending Recommendation Systems With Semantics And Context AwarenessExtending Recommendation Systems With Semantics And Context Awareness
Extending Recommendation Systems With Semantics And Context AwarenessVictor Codina
 
AI: Belief Networks
AI: Belief NetworksAI: Belief Networks
AI: Belief Networks
Datamining Tools
 
SVD and the Netflix Dataset
SVD and the Netflix DatasetSVD and the Netflix Dataset
SVD and the Netflix Dataset
Ben Mabey
 
SemanticSVD++: Incorporating Semantic Taste Evolution for Predicting Ratings
SemanticSVD++: Incorporating Semantic Taste Evolution for Predicting RatingsSemanticSVD++: Incorporating Semantic Taste Evolution for Predicting Ratings
SemanticSVD++: Incorporating Semantic Taste Evolution for Predicting Ratings
Matthew Rowe
 
Leveraging Knowledge Bases for Contextual Entity Exploration Categories
Leveraging Knowledge Basesfor Contextual Entity Exploration CategoriesLeveraging Knowledge Basesfor Contextual Entity Exploration Categories
Leveraging Knowledge Bases for Contextual Entity Exploration Categories
祺傑 林
 
最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - 最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に -
Hiroshi Fukui
 
Metrics for Evaluating Quality of Embeddings for Ontological Concepts
Metrics for Evaluating Quality of Embeddings for Ontological Concepts Metrics for Evaluating Quality of Embeddings for Ontological Concepts
Metrics for Evaluating Quality of Embeddings for Ontological Concepts
Saeedeh Shekarpour
 
Contextual Recommendation of Social Updates, a tag-based framework
Contextual Recommendation of Social Updates, a tag-based frameworkContextual Recommendation of Social Updates, a tag-based framework
Contextual Recommendation of Social Updates, a tag-based framework
Adrien Joly
 
Quality of Multimedia Experience: Past, Present and Future
Quality of Multimedia Experience: Past, Present and FutureQuality of Multimedia Experience: Past, Present and Future
Quality of Multimedia Experience: Past, Present and Future
Touradj Ebrahimi
 
Machine Learning: Classification Concepts (Part 1)
Machine Learning: Classification Concepts (Part 1)Machine Learning: Classification Concepts (Part 1)
Machine Learning: Classification Concepts (Part 1)
Daniel Chan
 
TunUp final presentation
TunUp final presentationTunUp final presentation
TunUp final presentation
Gianmario Spacagna
 
CLUSTERING
CLUSTERINGCLUSTERING
CLUSTERING
Aman Jatain
 
Recommendation system using collaborative deep learning
Recommendation system using collaborative deep learningRecommendation system using collaborative deep learning
Recommendation system using collaborative deep learning
Ritesh Sawant
 
Large Scale Image Retrieval 2022.pdf
Large Scale Image Retrieval 2022.pdfLarge Scale Image Retrieval 2022.pdf
Large Scale Image Retrieval 2022.pdf
SamuCerezo
 

Similar to [ECWEB2012]Differential Context Relaxation for Context-Aware Travel Recommendation (20)

CARR’13 - Semantically-Enhanced Pre-Filtering for CARS
CARR’13 - Semantically-Enhanced Pre-Filtering for CARSCARR’13 - Semantically-Enhanced Pre-Filtering for CARS
CARR’13 - Semantically-Enhanced Pre-Filtering for CARS
 
Download
DownloadDownload
Download
 
Download
DownloadDownload
Download
 
Transferring Semantic Categories with Vertex Kernels: Recommendations with Se...
Transferring Semantic Categories with Vertex Kernels: Recommendations with Se...Transferring Semantic Categories with Vertex Kernels: Recommendations with Se...
Transferring Semantic Categories with Vertex Kernels: Recommendations with Se...
 
LCBM: Statistics-Based Parallel Collaborative Filtering
LCBM: Statistics-Based Parallel Collaborative FilteringLCBM: Statistics-Based Parallel Collaborative Filtering
LCBM: Statistics-Based Parallel Collaborative Filtering
 
Extending Recommendation Systems With Semantics And Context Awareness
Extending Recommendation Systems With Semantics And Context AwarenessExtending Recommendation Systems With Semantics And Context Awareness
Extending Recommendation Systems With Semantics And Context Awareness
 
AI: Belief Networks
AI: Belief NetworksAI: Belief Networks
AI: Belief Networks
 
SVD and the Netflix Dataset
SVD and the Netflix DatasetSVD and the Netflix Dataset
SVD and the Netflix Dataset
 
SemanticSVD++: Incorporating Semantic Taste Evolution for Predicting Ratings
SemanticSVD++: Incorporating Semantic Taste Evolution for Predicting RatingsSemanticSVD++: Incorporating Semantic Taste Evolution for Predicting Ratings
SemanticSVD++: Incorporating Semantic Taste Evolution for Predicting Ratings
 
Leveraging Knowledge Bases for Contextual Entity Exploration Categories
Leveraging Knowledge Basesfor Contextual Entity Exploration CategoriesLeveraging Knowledge Basesfor Contextual Entity Exploration Categories
Leveraging Knowledge Bases for Contextual Entity Exploration Categories
 
最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - 最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に -
 
Metrics for Evaluating Quality of Embeddings for Ontological Concepts
Metrics for Evaluating Quality of Embeddings for Ontological Concepts Metrics for Evaluating Quality of Embeddings for Ontological Concepts
Metrics for Evaluating Quality of Embeddings for Ontological Concepts
 
Contextual Recommendation of Social Updates, a tag-based framework
Contextual Recommendation of Social Updates, a tag-based frameworkContextual Recommendation of Social Updates, a tag-based framework
Contextual Recommendation of Social Updates, a tag-based framework
 
Quality of Multimedia Experience: Past, Present and Future
Quality of Multimedia Experience: Past, Present and FutureQuality of Multimedia Experience: Past, Present and Future
Quality of Multimedia Experience: Past, Present and Future
 
Machine Learning: Classification Concepts (Part 1)
Machine Learning: Classification Concepts (Part 1)Machine Learning: Classification Concepts (Part 1)
Machine Learning: Classification Concepts (Part 1)
 
TunUp final presentation
TunUp final presentationTunUp final presentation
TunUp final presentation
 
CLUSTERING
CLUSTERINGCLUSTERING
CLUSTERING
 
10 clusbasic
10 clusbasic10 clusbasic
10 clusbasic
 
Recommendation system using collaborative deep learning
Recommendation system using collaborative deep learningRecommendation system using collaborative deep learning
Recommendation system using collaborative deep learning
 
Large Scale Image Retrieval 2022.pdf
Large Scale Image Retrieval 2022.pdfLarge Scale Image Retrieval 2022.pdf
Large Scale Image Retrieval 2022.pdf
 

More from YONG ZHENG

[ADMA 2017] Identification of Grey Sheep Users By Histogram Intersection In R...
[ADMA 2017] Identification of Grey Sheep Users By Histogram Intersection In R...[ADMA 2017] Identification of Grey Sheep Users By Histogram Intersection In R...
[ADMA 2017] Identification of Grey Sheep Users By Histogram Intersection In R...
YONG ZHENG
 
[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...
[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...
[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...
YONG ZHENG
 
[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies
[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies
[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies
YONG ZHENG
 
[WI 2017] Affective Prediction By Collaborative Chains In Movie Recommendation
[WI 2017] Affective Prediction By Collaborative Chains In Movie Recommendation[WI 2017] Affective Prediction By Collaborative Chains In Movie Recommendation
[WI 2017] Affective Prediction By Collaborative Chains In Movie Recommendation
YONG ZHENG
 
[IUI 2017] Criteria Chains: A Novel Multi-Criteria Recommendation Approach
[IUI 2017] Criteria Chains: A Novel Multi-Criteria Recommendation Approach[IUI 2017] Criteria Chains: A Novel Multi-Criteria Recommendation Approach
[IUI 2017] Criteria Chains: A Novel Multi-Criteria Recommendation Approach
YONG ZHENG
 
Tutorial: Context-awareness In Information Retrieval and Recommender Systems
Tutorial: Context-awareness In Information Retrieval and Recommender SystemsTutorial: Context-awareness In Information Retrieval and Recommender Systems
Tutorial: Context-awareness In Information Retrieval and Recommender Systems
YONG ZHENG
 
[EMPIRE 2016] Adapt to Emotional Reactions In Context-aware Personalization
[EMPIRE 2016] Adapt to Emotional Reactions In Context-aware Personalization[EMPIRE 2016] Adapt to Emotional Reactions In Context-aware Personalization
[EMPIRE 2016] Adapt to Emotional Reactions In Context-aware Personalization
YONG ZHENG
 
[UMAP 2016] User-Oriented Context Suggestion
[UMAP 2016] User-Oriented Context Suggestion[UMAP 2016] User-Oriented Context Suggestion
[UMAP 2016] User-Oriented Context Suggestion
YONG ZHENG
 
Tutorial: Context In Recommender Systems
Tutorial: Context In Recommender SystemsTutorial: Context In Recommender Systems
Tutorial: Context In Recommender Systems
YONG ZHENG
 
Context-aware Recommendation: A Quick View
Context-aware Recommendation: A Quick ViewContext-aware Recommendation: A Quick View
Context-aware Recommendation: A Quick View
YONG ZHENG
 
[IUI2015] A Revisit to The Identification of Contexts in Recommender Systems
[IUI2015] A Revisit to The Identification of Contexts in Recommender Systems[IUI2015] A Revisit to The Identification of Contexts in Recommender Systems
[IUI2015] A Revisit to The Identification of Contexts in Recommender Systems
YONG ZHENG
 
Matrix Factorization In Recommender Systems
Matrix Factorization In Recommender SystemsMatrix Factorization In Recommender Systems
Matrix Factorization In Recommender Systems
YONG ZHENG
 
[Decisions2013@RecSys]The Role of Emotions in Context-aware Recommendation
[Decisions2013@RecSys]The Role of Emotions in Context-aware Recommendation[Decisions2013@RecSys]The Role of Emotions in Context-aware Recommendation
[Decisions2013@RecSys]The Role of Emotions in Context-aware Recommendation
YONG ZHENG
 
[UMAP2013]Tutorial on Context-Aware User Modeling for Recommendation by Bamsh...
[UMAP2013]Tutorial on Context-Aware User Modeling for Recommendation by Bamsh...[UMAP2013]Tutorial on Context-Aware User Modeling for Recommendation by Bamsh...
[UMAP2013]Tutorial on Context-Aware User Modeling for Recommendation by Bamsh...
YONG ZHENG
 
A manual for Ph.D dissertation
A manual for Ph.D dissertationA manual for Ph.D dissertation
A manual for Ph.D dissertation
YONG ZHENG
 
Attention flow by tagging prediction
Attention flow by tagging predictionAttention flow by tagging prediction
Attention flow by tagging prediction
YONG ZHENG
 
[HetRec2011@RecSys]Experience Discovery: Hybrid Recommendation of Student Act...
[HetRec2011@RecSys]Experience Discovery: Hybrid Recommendation of Student Act...[HetRec2011@RecSys]Experience Discovery: Hybrid Recommendation of Student Act...
[HetRec2011@RecSys]Experience Discovery: Hybrid Recommendation of Student Act...
YONG ZHENG
 

More from YONG ZHENG (17)

[ADMA 2017] Identification of Grey Sheep Users By Histogram Intersection In R...
[ADMA 2017] Identification of Grey Sheep Users By Histogram Intersection In R...[ADMA 2017] Identification of Grey Sheep Users By Histogram Intersection In R...
[ADMA 2017] Identification of Grey Sheep Users By Histogram Intersection In R...
 
[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...
[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...
[RIIT 2017] Identifying Grey Sheep Users By The Distribution of User Similari...
 
[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies
[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies
[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies
 
[WI 2017] Affective Prediction By Collaborative Chains In Movie Recommendation
[WI 2017] Affective Prediction By Collaborative Chains In Movie Recommendation[WI 2017] Affective Prediction By Collaborative Chains In Movie Recommendation
[WI 2017] Affective Prediction By Collaborative Chains In Movie Recommendation
 
[IUI 2017] Criteria Chains: A Novel Multi-Criteria Recommendation Approach
[IUI 2017] Criteria Chains: A Novel Multi-Criteria Recommendation Approach[IUI 2017] Criteria Chains: A Novel Multi-Criteria Recommendation Approach
[IUI 2017] Criteria Chains: A Novel Multi-Criteria Recommendation Approach
 
Tutorial: Context-awareness In Information Retrieval and Recommender Systems
Tutorial: Context-awareness In Information Retrieval and Recommender SystemsTutorial: Context-awareness In Information Retrieval and Recommender Systems
Tutorial: Context-awareness In Information Retrieval and Recommender Systems
 
[EMPIRE 2016] Adapt to Emotional Reactions In Context-aware Personalization
[EMPIRE 2016] Adapt to Emotional Reactions In Context-aware Personalization[EMPIRE 2016] Adapt to Emotional Reactions In Context-aware Personalization
[EMPIRE 2016] Adapt to Emotional Reactions In Context-aware Personalization
 
[UMAP 2016] User-Oriented Context Suggestion
[UMAP 2016] User-Oriented Context Suggestion[UMAP 2016] User-Oriented Context Suggestion
[UMAP 2016] User-Oriented Context Suggestion
 
Tutorial: Context In Recommender Systems
Tutorial: Context In Recommender SystemsTutorial: Context In Recommender Systems
Tutorial: Context In Recommender Systems
 
Context-aware Recommendation: A Quick View
Context-aware Recommendation: A Quick ViewContext-aware Recommendation: A Quick View
Context-aware Recommendation: A Quick View
 
[IUI2015] A Revisit to The Identification of Contexts in Recommender Systems
[IUI2015] A Revisit to The Identification of Contexts in Recommender Systems[IUI2015] A Revisit to The Identification of Contexts in Recommender Systems
[IUI2015] A Revisit to The Identification of Contexts in Recommender Systems
 
Matrix Factorization In Recommender Systems
Matrix Factorization In Recommender SystemsMatrix Factorization In Recommender Systems
Matrix Factorization In Recommender Systems
 
[Decisions2013@RecSys]The Role of Emotions in Context-aware Recommendation
[Decisions2013@RecSys]The Role of Emotions in Context-aware Recommendation[Decisions2013@RecSys]The Role of Emotions in Context-aware Recommendation
[Decisions2013@RecSys]The Role of Emotions in Context-aware Recommendation
 
[UMAP2013]Tutorial on Context-Aware User Modeling for Recommendation by Bamsh...
[UMAP2013]Tutorial on Context-Aware User Modeling for Recommendation by Bamsh...[UMAP2013]Tutorial on Context-Aware User Modeling for Recommendation by Bamsh...
[UMAP2013]Tutorial on Context-Aware User Modeling for Recommendation by Bamsh...
 
A manual for Ph.D dissertation
A manual for Ph.D dissertationA manual for Ph.D dissertation
A manual for Ph.D dissertation
 
Attention flow by tagging prediction
Attention flow by tagging predictionAttention flow by tagging prediction
Attention flow by tagging prediction
 
[HetRec2011@RecSys]Experience Discovery: Hybrid Recommendation of Student Act...
[HetRec2011@RecSys]Experience Discovery: Hybrid Recommendation of Student Act...[HetRec2011@RecSys]Experience Discovery: Hybrid Recommendation of Student Act...
[HetRec2011@RecSys]Experience Discovery: Hybrid Recommendation of Student Act...
 

Recently uploaded

From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
Product School
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Albert Hoitingh
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
91mobiles
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
DianaGray10
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
Paul Groth
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
ControlCase
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
Safe Software
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
Kari Kakkonen
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
OnBoard
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
Dorra BARTAGUIZ
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
Product School
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Inflectra
 
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Product School
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
Thijs Feryn
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Thierry Lestable
 

Recently uploaded (20)

From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
 
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
 

[ECWEB2012]Differential Context Relaxation for Context-Aware Travel Recommendation

  • 1. Differential Context Relaxation for Context-Aware Travel Recomendation Yong Zheng, Robin Burke, Bamshad Mobasher Center for Web Intelligence DePaul University
  • 2. Recommender System  Any system that guides the user in a personalized way to interesting or useful objects in a large space of possible options or that produces such objects as output.  Context-aware recommendation  means that our definition of “useful” includes contextual considerations
  • 3. Normal Recommendation Profile Restaurant1 Rating1 Restaurant2 Rating2 ... ...
  • 4. Context-Aware Recommendation Profile Restaurant1 Rating1 Context1 Restaurant2 Rating2 Context2
  • 5. Approaches to CARS  Filtering  discard all options not appropriate to context  (either before or after)  Modeling  build context into recommendation model  Critical question  What contextual features matter?  The more context features we use  The more options are filtered out  The sparser the modeling space
  • 6. Context as constraints  We can view context-aware recommendation as imposing additional constraints on recommendation  Options must be suitable to the context  But we may be willing to relax these constraints to find nearby options
  • 7. Relaxation etc.
  • 8. Context matching  Assume we have a set of contextual features c  c = < f1, f2, f3, ... fn >  Define a set of constraints, C  Two contexts c and d match relative to constraints C iff  Each feature in c and d matches relative to the corresponding constraint in C
  • 9. Example: Hotel Ratings  { trip type, days stayed, origin city, destination city, month of departure }  c1 = {business, 3, Los Angeles, Chicago, July}  c2 = {business, 7, Seattle, Chicago, January}  Should they match or not?
  • 10. Matching with constraints  Two contexts  c1 = {business, 3, Los Angeles, Chicago, July}  c2 = {business, 7, Seattle, Chicago, January}  Cstrict = { (exact trip type), (exact duration), (exact origin), (exact destination), (exact month) }  no match  Crelaxed = { (exact trip type), (any duration), (contained time_zone origin), (exact destination), (any month) }  now the two contexts match  If we are predicting for a user in context c2,  we would not use a rating with context c1, if we apply constraint Cstrict  we would use it, if we apply Crelaxed
  • 11. Differential Context Relaxation  The idea is to apply context to different components of a recommendation algorithm  Rather than applying it in a uniform way  Example  kNN collaborative recommendation via Resnick’s algorithm Pred(u , i )  ru   vN wv  (rv ,i  rv ) w vN v
  • 12. Component 1: Neighbors  Original algorithm  Select neighbors who have rated item i  Context-aware  given context c  Select neighbors who have rated item i in context matching c, relative to constraint C1 Pred(u, i, c)  r   vN wv  (rv,i  rv ) u w v vN
  • 13. Component 2: Peer Baseline  Original algorithm  Average over all of the ratings by a neighbor to establish a baseline  Context-aware  given context C  Average over only those ratings matching c given constraint C2 Pred(u, i, c)  r   vN wv  (rv,i  rv ) u w v vN
  • 14. Component 3: User baseline  Original algorithm  Average over all of the target user’s ratings to establish a baseline  Context-aware  given context C  Average over the target users ratings given in contexts that match c, relative to constraint C3 Pred(u, i, c)  r   vN wv  (rv,i  rv ) u w v vN
  • 15. Question  How to choose C1, C2, C3 to make best use of the context information  In other words  what is the optimum relaxation of the contextual constraint  applied differentially to each algorithm component?
  • 16. Data set  Tripadvisor  Top 50 US cities  2,562 users  1,455 hotels  9,251 ratings  Fairly difficult recommendation task  some work using “Trip Type” as a contextual variable
  • 17. Context-linked features  We decided to use user location and hotel location as context features  Strictly speaking  demographic  content  However research in the travel domain (Klenosky and Gitelson, 1998) shows these factors influence user’s expectations  different standards for a California hotel vs a Nevada one  behave like contextual features  We call these “context-linked” features
  • 18. Feature space  trip type – solo, family, business, etc.  origin city  contained state  contained time zone  destination city  contained state  contained time zone  Total of 32 possibilities
  • 19. Optimization  32 feature possibilities  3 components  323 = 32k possible constraint combinations  But possible to eliminate some possibilities  Example  when averaging over a given user’s ratings  user location is irrelevant  will not filter anything out  Able to shrink to < 400 combinations  enough for exhaustive search
  • 23. Differential Context Relaxation  Lets us incorporate context  While managing the tradeoff between accuracy and coverage  Future considerations  other algorithms  F1 optimization constraint  instead of binary matching, real-valued?  instead of selection, weighting of features?  scalable optimization  Stay tuned!  RecSys CARS workshop Yong Zheng, Robin Burke, Bamshad Mobasher. "Optimal Feature Selection for Context-Aware Recommendation using Differential Relaxation". Proceedings of the 4th International Workshop on Context-Aware Recommender Systems (CARS 2012) held in conjunction with the 6th ACM Conference on Recommender Systems (RecSys 2012), Dublin, Ireland, Sep 2012