Libraries Recommender System

Implementation Time:
9 months
Solution Provider: AI Singapore

NUS is ranked consistently as one of the world’s top universities. They offer the most extensive college degree courses in Singapore. The NUS Libraries comprises eight libraries. They support teaching and research for various schools, faculties, and their graduate divisions as well as administrative units and research institutes.

  • NUS Libraries launched a unified search system called FindMore in Dec 2019 that performs a search across multiple internal and external databases and consolidates the results to the users
  • NUS Libraries wishes to augment the search engine with a recommender system, so as to provide a more personalised experience for users, and to encourage them to read more by uncovering more diverse yet relevant items

How can NUS Libraries use AI to:

  1. Engage library users better by analysing their users’ profiles and reading history, in order to recommend items that might be of high relevance and interest
  2. Increase the range of items being transacted given their rich database of items

An AI recommender system was deployed on the FindMore portal as an endpoint.

  • The engine takes in a query in real-time and returns a list of alternative recommended items to complement the default search results
  • The model learns from i) the search term’s natural language features ii) titles/descriptions of items in the database iii) historical transactions between every user and item in the database
  • The system can also make recommendations to NUS Libraries’ email subscribers on a weekly basis based on the user’s profile, preference and transactional history to suggest relevant items

Outcomes

  • The recommender engine achieved a click-to-open rate that is 4x higher than the global benchmark for the Education and Training industry
  • The team delivered a pipeline to automatically consume incremental data and update the model accordingly, re-serving the query application and generating new recommendations for email subscribers
  • The solution was tested for deployment in NUS Libraries’ production environment and will be integrated as a beta version when the upgraded FindMore portal goes live

 

PDF Document

Download Brochure

This is the last content of this tab. If you do not see any resources above, it means the solution provider have not provided any resources. Feel free to contact Solution Provider for more information.

Contact Us
The enquirer name
Company Name

Implementation Time

9 months

Use Case Brochure