Vipshop's Personalized Recommender System

Vipshop is a leading online discount retailer for brands in China. The company offers high quality and popular branded products to consumers throughout China at a significant discount from retail prices. To optimize the shopping experience for their customers, the company built a personalized search recommendation system based on user query keywords and user portraits. Milvus, an open-source vector database built by Zilliz, is used to power the personalized recommender system on Vipshop’s mobile apps.
Objective
Build an e-commerce search recommendation system is to retrieve suitable products from a large number of products and display them to users according to their search intent and preference.
Challenges
- Long computational response time - the average latency to retrieve TopK results from millions of items is around 300 ms. - High maintenance cost of ElasticSearch indexes - the same set of indexes is used for both commodity feature vectors and other related data, which hardly facilitates index building, but produces a massive amount of data.
Why verctor database
- Support for various mainstream indexes makes vector search blazing fast. - Support for incremental and entire data update. - Support for distributed deployment, multi-language SDKs, and read/write separation.
Results
- Searches on million-vector datasets complete in 30 milliseconds, approximately ten times faster than the previous solution adopted by Vipshop. - Provides accurate recommendations to users to optimize their shopping experience.
"At present, Milvus-based vector search can be used steadily in recommendation system scenarios, and its high performance gives us more room to play in the dimensionality of model and algorithm selection."
Read the full storyshare this
