Learning dynamic insurance recommendations from users' click sessions
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Learning dynamic insurance recommendations from users' click sessions. / Bruun, Simone Borg.
RecSys 2021 - 15th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc., 2021. p. 860-863 (RecSys 2021 - 15th ACM Conference on Recommender Systems).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Learning dynamic insurance recommendations from users' click sessions
AU - Bruun, Simone Borg
N1 - Publisher Copyright: © 2021 Owner/Author.
PY - 2021/9/13
Y1 - 2021/9/13
N2 - While personalised recommendations have been most successful in domains like retail due to large volume of users' feedback on items, it is challenging to implement traditional recommender systems into the insurance domain where such prior information is very small in volume. This work addresses the problem of sparse feedback by studying users' click sessions as signals for learning insurance recommendations. Our preliminary results show limitations in representing click sessions by manually engineered features. The proposed framework uses an autoencoder approach to automatically learns representation of sessions, then a neural network approach to model dependencies across sessions that can be used to predict recommendations. Thereby, it is further able to capture users' dynamic needs of insurance products evolving over time.
AB - While personalised recommendations have been most successful in domains like retail due to large volume of users' feedback on items, it is challenging to implement traditional recommender systems into the insurance domain where such prior information is very small in volume. This work addresses the problem of sparse feedback by studying users' click sessions as signals for learning insurance recommendations. Our preliminary results show limitations in representing click sessions by manually engineered features. The proposed framework uses an autoencoder approach to automatically learns representation of sessions, then a neural network approach to model dependencies across sessions that can be used to predict recommendations. Thereby, it is further able to capture users' dynamic needs of insurance products evolving over time.
KW - Click-based models
KW - Insurance domain
KW - Session-based recommender systems
U2 - 10.1145/3460231.3473900
DO - 10.1145/3460231.3473900
M3 - Article in proceedings
AN - SCOPUS:85115613496
T3 - RecSys 2021 - 15th ACM Conference on Recommender Systems
SP - 860
EP - 863
BT - RecSys 2021 - 15th ACM Conference on Recommender Systems
PB - Association for Computing Machinery, Inc.
T2 - 15th ACM Conference on Recommender Systems, RecSys 2021
Y2 - 27 September 2021 through 1 October 2021
ER -
ID: 306689949