Evaluating recommender systems in feature model configuration.

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review


Configurators can be evaluated in various ways such as efficiency and completeness of solution search, optimality of the proposed solutions, usability of configurator user interfaces, and configuration consistency. Due to the increasing size and complexity of feature models, the integration of recommendation algorithms with feature model configurators becomes relevant. In this paper, we show how the output of a recommender system can be evaluated within the scope of feature model configuration scenarios. Overall, we argue that the discussed ways of measuring recommendation quality help developers to gain a broader view on evaluation techniques in constraint-based recommendation domains.
Original languageEnglish
Title of host publicationProceedings of the 25th ACM International Systems and Software Product Line Conference, SPLC 2021
EditorsMohammad Mousavi, Pierre-Yves Schobbens, Hugo Araujo, Ina Schaefer, Maurice H. ter Beek, Xavier Devroey, Jose Miguel Rojas, Monica Pinto, Leopoldo Teixeira, Thorsten Berger, Johannes Noppen, Iris Reinhartz-Berger, Paul Temple, Ferruccio Damiani, Justyna Petke
PublisherAssociation of Computing Machinery
Number of pages6
ISBN (Electronic)978-1-4503-8469-8
Publication statusPublished - 6 Sept 2021
Event25th ACM International Systems and Software Product Line Conference: SPLC'21 - Virtuell, United Kingdom
Duration: 6 Sept 202111 Sept 2021


Conference25th ACM International Systems and Software Product Line Conference
Abbreviated titleSPLC'21
Country/TerritoryUnited Kingdom
Internet address


  • configuration
  • evaluation
  • feature models
  • recommender systems

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications


Dive into the research topics of 'Evaluating recommender systems in feature model configuration.'. Together they form a unique fingerprint.

Cite this