Personalized fund recommendation with dynamic utility learning
Abstract This study introduces a fund recommendation system based on the $$\epsilon$$ ϵ -greedy algorithm and an incremental learning framework. This model simulates the interaction process when customers browse the web-pages of fund products. Customers click on their preferred fund products when vi...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | Financial Innovation |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40854-024-00720-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594458627014656 |
|---|---|
| author | Jiaxin Wei Jia Liu |
| author_facet | Jiaxin Wei Jia Liu |
| author_sort | Jiaxin Wei |
| collection | DOAJ |
| description | Abstract This study introduces a fund recommendation system based on the $$\epsilon$$ ϵ -greedy algorithm and an incremental learning framework. This model simulates the interaction process when customers browse the web-pages of fund products. Customers click on their preferred fund products when visiting a fund recommendation web-page. The system collects customer click sequences to continually estimate and update their utility function. The system generates product lists using the $$\epsilon$$ ϵ -greedy algorithm, where each product on the list has the probability of 1- $$\epsilon$$ ϵ of being selected as an exploitation strategy, and the probability of $$\epsilon$$ ϵ is chosen as the exploration strategy. We perform a series of numerical tests to evaluate the estimation performance with different values of $$\epsilon$$ ϵ . |
| format | Article |
| id | doaj-art-129158c115c84d94b576dd1431872504 |
| institution | Kabale University |
| issn | 2199-4730 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Financial Innovation |
| spelling | doaj-art-129158c115c84d94b576dd14318725042025-01-19T12:36:02ZengSpringerOpenFinancial Innovation2199-47302025-01-0111112710.1186/s40854-024-00720-5Personalized fund recommendation with dynamic utility learningJiaxin Wei0Jia Liu1School of Mathematics and Statistics, Xi’an Jiaotong UniversitySchool of Mathematics and Statistics, Xi’an Jiaotong UniversityAbstract This study introduces a fund recommendation system based on the $$\epsilon$$ ϵ -greedy algorithm and an incremental learning framework. This model simulates the interaction process when customers browse the web-pages of fund products. Customers click on their preferred fund products when visiting a fund recommendation web-page. The system collects customer click sequences to continually estimate and update their utility function. The system generates product lists using the $$\epsilon$$ ϵ -greedy algorithm, where each product on the list has the probability of 1- $$\epsilon$$ ϵ of being selected as an exploitation strategy, and the probability of $$\epsilon$$ ϵ is chosen as the exploration strategy. We perform a series of numerical tests to evaluate the estimation performance with different values of $$\epsilon$$ ϵ .https://doi.org/10.1186/s40854-024-00720-5Personalized fund recommendation$$\epsilon$$ ϵ -greedy algorithmDynamic utility learning |
| spellingShingle | Jiaxin Wei Jia Liu Personalized fund recommendation with dynamic utility learning Financial Innovation Personalized fund recommendation $$\epsilon$$ ϵ -greedy algorithm Dynamic utility learning |
| title | Personalized fund recommendation with dynamic utility learning |
| title_full | Personalized fund recommendation with dynamic utility learning |
| title_fullStr | Personalized fund recommendation with dynamic utility learning |
| title_full_unstemmed | Personalized fund recommendation with dynamic utility learning |
| title_short | Personalized fund recommendation with dynamic utility learning |
| title_sort | personalized fund recommendation with dynamic utility learning |
| topic | Personalized fund recommendation $$\epsilon$$ ϵ -greedy algorithm Dynamic utility learning |
| url | https://doi.org/10.1186/s40854-024-00720-5 |
| work_keys_str_mv | AT jiaxinwei personalizedfundrecommendationwithdynamicutilitylearning AT jialiu personalizedfundrecommendationwithdynamicutilitylearning |