Serendipitous Personalized Ranking for Top-N Recommendation

Serendipitous recommendation has benefitted both e-retailers and users. It tends to suggest items which are both unexpected and useful to users. These items are not only profitable to the retailers but also surprisingly suitable to consumers' tastes. However, due to the imbalance in observed da...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology Ročník 1; s. 258 - 265
Hlavní autoři: Lu, Qiuxia, Chen, Tianqi, Zhang, Weinan, Yang, Diyi, Yu, Yong
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.12.2012
Témata:
Accuracy
Collaborative filtering
Hands
Logistics
Mathematical models
Matrix Factorization
Measurement
Optimization
Predictive models
Recommender systems
Serendipity
Training
ISBN:9781467360579, 1467360570
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Serendipitous recommendation has benefitted both e-retailers and users. It tends to suggest items which are both unexpected and useful to users. These items are not only profitable to the retailers but also surprisingly suitable to consumers' tastes. However, due to the imbalance in observed data for popular and tail items, existing collaborative filtering methods fail to give satisfactory serendipitous recommendations. To solve this problem, we propose a simple and effective method, called serendipitous personalized ranking. The experimental results demonstrate that our method significantly improves both accuracy and serendipity for top-N recommendation compared to traditional personalized ranking methods in various settings.
ISBN:9781467360579
1467360570
DOI:10.1109/WI-IAT.2012.135