Account-based recommenders in open discovery environments

Jim Hahn, Courtney McDonald

Research output: Contribution to journalArticlepeer-review


Purpose: This paper aims to introduce a machine learning-based “My Account” recommender for implementation in open discovery environments such as VuFind among others. Design/methodology/approach: The approach to implementing machine learning-based personalized recommenders is undertaken as applied research leveraging data streams of transactional checkout data from discovery systems. Findings: The authors discuss the need for large data sets from which to build an algorithm and introduce a prototype recommender service, describing the prototype’s data flow pipeline and machine learning processes. Practical implications: The browse paradigm of discovery has neglected to leverage discovery system data to inform the development of personalized recommendations; with this paper, the authors show novel approaches to providing enhanced browse functionality by way of a user account. Originality/value: In the age of big data and machine learning, advances in deep learning technology and data stream processing make it possible to leverage discovery system data to inform the development of personalized recommendations.

Original languageEnglish (US)
Pages (from-to)70-76
Number of pages7
JournalDigital Library Perspectives
Issue number1
StatePublished - 2018


  • Discovery
  • Machine learning
  • Open algorithm
  • Personalization
  • Recommendations
  • Research libraries

ASJC Scopus subject areas

  • Information Systems
  • Education
  • Library and Information Sciences


Dive into the research topics of 'Account-based recommenders in open discovery environments'. Together they form a unique fingerprint.

Cite this