Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Engage Grants Program

University of Alberta

$25,000.00

Recommendation Algorithms for Tourism and Destination Marketing based on Time-Varying Interest Modelling and Multiple Data Sources

EF 2014-15

Résumé
VISATOCHINA Group aims to develop a set of tourism and flight recommendation algorithms and integratethem into their subsidiary e-commerce tourism service: www.visatochina.ca, based on extensive data miningand machine learning from past transaction records, registered user profiles and various other data sourcesincluding followers on online social networks. The proposed project is to develop destination/tour/flightrecommendation algorithms that can model the time-varying interests of clients that may change over seasonsand time, and can scale to a large number of users, products and time periods. More data for learning can alsobe crawled from the large number of followers of VISATOCHINA on certain online social networking sites. Inthis project, unlike traditional static recommendation systems that use collaborative filtering to handle staticuser-item interest estimation, we introduce a time dimension and propose to model the changing time-varyinguser interests into destinations and tour products as a 3-D sparse array, where the known entries are calculatedbased on past transaction records. Then we propose to apply various techniques to recover all the missingvalues from this sparse 3-D matrix, especially interest estimates in the current time period, using low-rankmatrix completion and tensor analysis. Moreover, additional information will be crawled from socialnetworking sites to help understand user's recent status and estimate the initial interests of new users with noprior booking record. The proposed recommendation algorithms will be integrated into the online systems ofVISATOCHINA in multiple forms, including a recommendation email sending system, personalizedadvertisements on the web based on user login and user IP, as well as automatic message posts on socialnetworking sites. During the project, we will meet the company technical and administrative representatives ona weekly basis, and closely collaborate with the company software developers on data collection,recommendation algorithm implementation, and to integrate the developed recommendation system intovarious production online services.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
476711-2014
Name nom
Niu, Di
Department département
Electrical and Computer Engineering
Organization id
9
Institution établissement
University of Alberta
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2014
Competition year année de concours
2014
Award amount
25000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1555
Committee name en
Prairie Internal Decision Committee
Committee name fr
Comité de décision interne pour les Prairies
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2805
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Learning and inference theories
Research subject fr
Théories de l'apprentissage et l'inférence
Partie
1
Nb partie
1
Application title
Recommendation Algorithms for Tourism and Destination Marketing based on Time-Varying Interest Modelling and Multiple Data Sources
Keyword
NSERC
Application summary
VISATOCHINA Group aims to develop a set of tourism and flight recommendation algorithms and integratethem into their subsidiary e-commerce tourism service: www.visatochina.ca, based on extensive data miningand machine learning from past transaction records, registered user profiles and various other data sourcesincluding followers on online social networks. The proposed project is to develop destination/tour/flightrecommendation algorithms that can model the time-varying interests of clients that may change over seasonsand time, and can scale to a large number of users, products and time periods. More data for learning can alsobe crawled from the large number of followers of VISATOCHINA on certain online social networking sites. Inthis project, unlike traditional static recommendation systems that use collaborative filtering to handle staticuser-item interest estimation, we introduce a time dimension and propose to model the changing time-varyinguser interests into destinations and tour products as a 3-D sparse array, where the known entries are calculatedbased on past transaction records. Then we propose to apply various techniques to recover all the missingvalues from this sparse 3-D matrix, especially interest estimates in the current time period, using low-rankmatrix completion and tensor analysis. Moreover, additional information will be crawled from socialnetworking sites to help understand user's recent status and estimate the initial interests of new users with noprior booking record. The proposed recommendation algorithms will be integrated into the online systems ofVISATOCHINA in multiple forms, including a recommendation email sending system, personalizedadvertisements on the web based on user login and user IP, as well as automatic message posts on socialnetworking sites. During the project, we will meet the company technical and administrative representatives ona weekly basis, and closely collaborate with the company software developers on data collection,recommendation algorithm implementation, and to integrate the developed recommendation system intovarious production online services.