A two-stage recommendation optimization algorithm based on item popularity and user features
Financial product recommendation algorithms are mainly product-centered. This article proposes a two-stage recommendation optimization algorithm based on item popularity and user features, named CPCF-TSP, that can make full use of the demographic characteristics of users and mitigate the problem of...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-10-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024142260 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850264178232655872 |
|---|---|
| author | Jun Wang Rongjie Hu |
| author_facet | Jun Wang Rongjie Hu |
| author_sort | Jun Wang |
| collection | DOAJ |
| description | Financial product recommendation algorithms are mainly product-centered. This article proposes a two-stage recommendation optimization algorithm based on item popularity and user features, named CPCF-TSP, that can make full use of the demographic characteristics of users and mitigate the problem of users being more inclined to choose “hot” financial products. A popularity weight factor is introduced to normalize popularity and modify Pearson's similarity function. The modified Pearson's similarity function is combined with popularity normalization and user features to improve modeling performance. The two-stage recommendation optimization procedure was combined with a collaborative filtering algorithm to improve recommendation precision. CPCF-TSP fully considers user features in building a hybrid recommendation model and solves the problem of user cold-start. It can also mitigate popularity deviations and improve recommendation precision. MovieLens data and Santander Bank client trading data were used in a case study. The results show that the algorithm reduces inaccuracy in the calculation of the weights for recommendation popularity and similarity and is especially suitable for recommending financial products in which user information can be easily collected and the number of users is far greater than the number of products considered. |
| format | Article |
| id | doaj-art-a90f9ab1bd824ab89e547ad3dbeffdb9 |
| institution | OA Journals |
| issn | 2405-8440 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj-art-a90f9ab1bd824ab89e547ad3dbeffdb92025-08-20T01:54:45ZengElsevierHeliyon2405-84402024-10-011019e3819510.1016/j.heliyon.2024.e38195A two-stage recommendation optimization algorithm based on item popularity and user featuresJun Wang0Rongjie Hu1Corresponding author.; School of Mathematics & Statistic, Changchun University of Technology, Changchun, ChinaSchool of Mathematics & Statistic, Changchun University of Technology, Changchun, ChinaFinancial product recommendation algorithms are mainly product-centered. This article proposes a two-stage recommendation optimization algorithm based on item popularity and user features, named CPCF-TSP, that can make full use of the demographic characteristics of users and mitigate the problem of users being more inclined to choose “hot” financial products. A popularity weight factor is introduced to normalize popularity and modify Pearson's similarity function. The modified Pearson's similarity function is combined with popularity normalization and user features to improve modeling performance. The two-stage recommendation optimization procedure was combined with a collaborative filtering algorithm to improve recommendation precision. CPCF-TSP fully considers user features in building a hybrid recommendation model and solves the problem of user cold-start. It can also mitigate popularity deviations and improve recommendation precision. MovieLens data and Santander Bank client trading data were used in a case study. The results show that the algorithm reduces inaccuracy in the calculation of the weights for recommendation popularity and similarity and is especially suitable for recommending financial products in which user information can be easily collected and the number of users is far greater than the number of products considered.http://www.sciencedirect.com/science/article/pii/S2405844024142260Collaborative filteringHybrid recommendationUser featuresPopularity normalization |
| spellingShingle | Jun Wang Rongjie Hu A two-stage recommendation optimization algorithm based on item popularity and user features Heliyon Collaborative filtering Hybrid recommendation User features Popularity normalization |
| title | A two-stage recommendation optimization algorithm based on item popularity and user features |
| title_full | A two-stage recommendation optimization algorithm based on item popularity and user features |
| title_fullStr | A two-stage recommendation optimization algorithm based on item popularity and user features |
| title_full_unstemmed | A two-stage recommendation optimization algorithm based on item popularity and user features |
| title_short | A two-stage recommendation optimization algorithm based on item popularity and user features |
| title_sort | two stage recommendation optimization algorithm based on item popularity and user features |
| topic | Collaborative filtering Hybrid recommendation User features Popularity normalization |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024142260 |
| work_keys_str_mv | AT junwang atwostagerecommendationoptimizationalgorithmbasedonitempopularityanduserfeatures AT rongjiehu atwostagerecommendationoptimizationalgorithmbasedonitempopularityanduserfeatures AT junwang twostagerecommendationoptimizationalgorithmbasedonitempopularityanduserfeatures AT rongjiehu twostagerecommendationoptimizationalgorithmbasedonitempopularityanduserfeatures |