Personalized Product Service Recommendation Based on User Portrait Mathematical Model
- DOI
- 10.2991/cecs-18.2018.57How to use a DOI?
- Keywords
- big data, user portrait, customer rating, similarity, collaborative filtering.
- Abstract
In the “Internet+” digital age, the use of customers’ information was not fully utilized when pushed the information. The traditional similarity exists some problems, such as incalculable, indistinguishable and high-level etc., it results in poor pertinence of personalized product services and a decline in the quality of recommendations. Concerning this shortcoming, this paper proposes a collaborative filtering recommendation algorithm based on the user's portrait model customer rating, and use the customer's rating results to make recommendations. To this end, a “user portrait” mathematical model was constructed, the similarity was improved by using a discrete-volume correlation theory and was weighted approaching to the users’ preference. It would be more accurate for “K” nearest neighbor set by similarity calculation. Furthermore, this paper recommends more suitable products to users. The experiment was conducted with the customer's sales data of Le Bee net Cosmetics, it shows that the method proposed in the paper improves the accuracy of the recommendation effectively and improves the recommendation quality to some extent.
- Copyright
- © 2018, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Xuesheng Lai AU - Lili He AU - Qingyan Zhou PY - 2018/07 DA - 2018/07 TI - Personalized Product Service Recommendation Based on User Portrait Mathematical Model BT - Proceedings of the 2018 International Symposium on Communication Engineering & Computer Science (CECS 2018) PB - Atlantis Press SP - 328 EP - 333 SN - 2352-538X UR - https://doi.org/10.2991/cecs-18.2018.57 DO - 10.2991/cecs-18.2018.57 ID - Lai2018/07 ER -