Abstract
We present ShoppingAdvisor, a novel recommender system that helps users in shopping for technical products. ShoppingAdvisor leverages both user preferences and technical product attributes in order to generate its suggestions. The system elicits user preferences via a tree-shaped owchart, where each node is a question to the user. At each node, ShoppingAdvisor suggests a ranking of products matching the preferences of the user, and that gets progressively refined along the path from the tree's root to one of its leafs. In this paper we show (i) how to learn the structure of the tree, i.e., which questions to ask at each node, and (ii) how to produce a suitable ranking at each node. First, we adapt the classical top-down strategy for building decision trees in order to find the best user attribute to ask at each node. Differently from decision trees, ShoppingAdvisor partitions the user space rather than the product space. Second, we show how to employ a learning-To-rank approach in order to learn, for each node of the tree, a ranking of products appropriate to the users who reach that node. We experiment with two real-world datasets for cars and cameras, and a synthetic one. We use mean reciprocal rank to evaluate ShoppingAdvisor, and show how the performance increases by more than 50% along the path from root to leaf. We also show how collaborative recommendation algorithms such as k-nearest neighbor benefits from feature selection done by the ShoppingAdvisor tree. Our experiments show that ShoppingAdvisor produces good quality interpretable recommendations, while requiring less input from users and being able to handle the cold-start problem.
| Original language | English |
|---|---|
| Title of host publication | KDD 2013 - 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining |
| Publisher | Association for Computing Machinery |
| Pages | 203-211 |
| Number of pages | 9 |
| Volume | Part F128815 |
| ISBN (Electronic) | 9781450321747 |
| DOIs | |
| Publication status | Published - 11 Aug 2013 |
| Event | 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2013 - Chicago, United States Duration: 11 Aug 2013 → 14 Aug 2013 |
Other
| Other | 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2013 |
|---|---|
| Country | United States |
| City | Chicago |
| Period | 11/8/13 → 14/8/13 |
Fingerprint
Keywords
- Collaborative content
- Learning
- Ranking
- Recommendation
ASJC Scopus subject areas
- Software
- Information Systems
Cite this
Learning to question : Leveraging user preferences for shopping advice. / Das, Mahashweta; Morales, Gianmarco; Gionis, Aristides; Weber, Ingmar.
KDD 2013 - 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. Part F128815 Association for Computing Machinery, 2013. p. 203-211 2487653.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Learning to question
T2 - Leveraging user preferences for shopping advice
AU - Das, Mahashweta
AU - Morales, Gianmarco
AU - Gionis, Aristides
AU - Weber, Ingmar
PY - 2013/8/11
Y1 - 2013/8/11
N2 - We present ShoppingAdvisor, a novel recommender system that helps users in shopping for technical products. ShoppingAdvisor leverages both user preferences and technical product attributes in order to generate its suggestions. The system elicits user preferences via a tree-shaped owchart, where each node is a question to the user. At each node, ShoppingAdvisor suggests a ranking of products matching the preferences of the user, and that gets progressively refined along the path from the tree's root to one of its leafs. In this paper we show (i) how to learn the structure of the tree, i.e., which questions to ask at each node, and (ii) how to produce a suitable ranking at each node. First, we adapt the classical top-down strategy for building decision trees in order to find the best user attribute to ask at each node. Differently from decision trees, ShoppingAdvisor partitions the user space rather than the product space. Second, we show how to employ a learning-To-rank approach in order to learn, for each node of the tree, a ranking of products appropriate to the users who reach that node. We experiment with two real-world datasets for cars and cameras, and a synthetic one. We use mean reciprocal rank to evaluate ShoppingAdvisor, and show how the performance increases by more than 50% along the path from root to leaf. We also show how collaborative recommendation algorithms such as k-nearest neighbor benefits from feature selection done by the ShoppingAdvisor tree. Our experiments show that ShoppingAdvisor produces good quality interpretable recommendations, while requiring less input from users and being able to handle the cold-start problem.
AB - We present ShoppingAdvisor, a novel recommender system that helps users in shopping for technical products. ShoppingAdvisor leverages both user preferences and technical product attributes in order to generate its suggestions. The system elicits user preferences via a tree-shaped owchart, where each node is a question to the user. At each node, ShoppingAdvisor suggests a ranking of products matching the preferences of the user, and that gets progressively refined along the path from the tree's root to one of its leafs. In this paper we show (i) how to learn the structure of the tree, i.e., which questions to ask at each node, and (ii) how to produce a suitable ranking at each node. First, we adapt the classical top-down strategy for building decision trees in order to find the best user attribute to ask at each node. Differently from decision trees, ShoppingAdvisor partitions the user space rather than the product space. Second, we show how to employ a learning-To-rank approach in order to learn, for each node of the tree, a ranking of products appropriate to the users who reach that node. We experiment with two real-world datasets for cars and cameras, and a synthetic one. We use mean reciprocal rank to evaluate ShoppingAdvisor, and show how the performance increases by more than 50% along the path from root to leaf. We also show how collaborative recommendation algorithms such as k-nearest neighbor benefits from feature selection done by the ShoppingAdvisor tree. Our experiments show that ShoppingAdvisor produces good quality interpretable recommendations, while requiring less input from users and being able to handle the cold-start problem.
KW - Collaborative content
KW - Learning
KW - Ranking
KW - Recommendation
UR - http://www.scopus.com/inward/record.url?scp=85006080387&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85006080387&partnerID=8YFLogxK
U2 - 10.1145/2487575.2487653
DO - 10.1145/2487575.2487653
M3 - Conference contribution
AN - SCOPUS:85006080387
VL - Part F128815
SP - 203
EP - 211
BT - KDD 2013 - 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
PB - Association for Computing Machinery
ER -