Clus-DR: Cluster-based pre-trained model for diverse recommendation generation
Recommender Systems are a predictive model for personalized suggestions utilizing past interactions and experiences. Collaborative filtering is the most popular and successful approach. The core idea behind this approach is that the users expressing similar preferences in the past are considered sim...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-09-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S131915782200043X |
| _version_ | 1811188584375386112 |
|---|---|
| author | Naina Yadav Sukomal Pal Anil Kumar Singh Kartikey Singh |
| author_facet | Naina Yadav Sukomal Pal Anil Kumar Singh Kartikey Singh |
| author_sort | Naina Yadav |
| collection | DOAJ |
| description | Recommender Systems are a predictive model for personalized suggestions utilizing past interactions and experiences. Collaborative filtering is the most popular and successful approach. The core idea behind this approach is that the users expressing similar preferences in the past are considered similar and will continue to like similar recommendations in future. The similarity among the items between past and future references, however, affects diversity and coverage of the recommendation system. In this work, we focus on a less usual direction for recommendation systems by increasing the probability of retrieving unusual and novel items in the recommendation list, which are, or can be, also relevant to the users. Most of prevailing techniques for incorporating diversity are based on re-ranking methodology, which shrinks the domain of user’s exposure to serendipitous items. To overcome this issue, we propose a methodology Clus-DR (Cluster-based Diversity Recommendation) that uses individual diversity of users and then pre-trained model for diverse recommendation generation. Instead of relying on re-ranking approach, we use different clustering techniques to have different groups of users with similar diversity. Experimental results using datasets of diverse domains indicate the effectiveness of the proposed Clus-DR methodology in diversity and coverage while maintaining acceptable level of accuracy. |
| first_indexed | 2024-04-11T14:21:16Z |
| format | Article |
| id | doaj.art-75986ace95944176b860c2e976e3cdfd |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-04-11T14:21:16Z |
| publishDate | 2022-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-75986ace95944176b860c2e976e3cdfd2022-12-22T04:19:03ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782022-09-0134863856399Clus-DR: Cluster-based pre-trained model for diverse recommendation generationNaina Yadav0Sukomal Pal1Anil Kumar Singh2Kartikey Singh3Department of Computer Science and Engineering, IIT(BHU), Varanasi, Uttar Pradesh 221005, IndiaCorresponding author.; Department of Computer Science and Engineering, IIT(BHU), Varanasi, Uttar Pradesh 221005, IndiaDepartment of Computer Science and Engineering, IIT(BHU), Varanasi, Uttar Pradesh 221005, IndiaDepartment of Computer Science and Engineering, IIT(BHU), Varanasi, Uttar Pradesh 221005, IndiaRecommender Systems are a predictive model for personalized suggestions utilizing past interactions and experiences. Collaborative filtering is the most popular and successful approach. The core idea behind this approach is that the users expressing similar preferences in the past are considered similar and will continue to like similar recommendations in future. The similarity among the items between past and future references, however, affects diversity and coverage of the recommendation system. In this work, we focus on a less usual direction for recommendation systems by increasing the probability of retrieving unusual and novel items in the recommendation list, which are, or can be, also relevant to the users. Most of prevailing techniques for incorporating diversity are based on re-ranking methodology, which shrinks the domain of user’s exposure to serendipitous items. To overcome this issue, we propose a methodology Clus-DR (Cluster-based Diversity Recommendation) that uses individual diversity of users and then pre-trained model for diverse recommendation generation. Instead of relying on re-ranking approach, we use different clustering techniques to have different groups of users with similar diversity. Experimental results using datasets of diverse domains indicate the effectiveness of the proposed Clus-DR methodology in diversity and coverage while maintaining acceptable level of accuracy.http://www.sciencedirect.com/science/article/pii/S131915782200043XAggregate diversityDiversificationCollaborative filteringMatrix factorizationRecommender system |
| spellingShingle | Naina Yadav Sukomal Pal Anil Kumar Singh Kartikey Singh Clus-DR: Cluster-based pre-trained model for diverse recommendation generation Journal of King Saud University: Computer and Information Sciences Aggregate diversity Diversification Collaborative filtering Matrix factorization Recommender system |
| title | Clus-DR: Cluster-based pre-trained model for diverse recommendation generation |
| title_full | Clus-DR: Cluster-based pre-trained model for diverse recommendation generation |
| title_fullStr | Clus-DR: Cluster-based pre-trained model for diverse recommendation generation |
| title_full_unstemmed | Clus-DR: Cluster-based pre-trained model for diverse recommendation generation |
| title_short | Clus-DR: Cluster-based pre-trained model for diverse recommendation generation |
| title_sort | clus dr cluster based pre trained model for diverse recommendation generation |
| topic | Aggregate diversity Diversification Collaborative filtering Matrix factorization Recommender system |
| url | http://www.sciencedirect.com/science/article/pii/S131915782200043X |
| work_keys_str_mv | AT nainayadav clusdrclusterbasedpretrainedmodelfordiverserecommendationgeneration AT sukomalpal clusdrclusterbasedpretrainedmodelfordiverserecommendationgeneration AT anilkumarsingh clusdrclusterbasedpretrainedmodelfordiverserecommendationgeneration AT kartikeysingh clusdrclusterbasedpretrainedmodelfordiverserecommendationgeneration |