Addressing scalability in API method call analytics

Ervina Cergani, Sebastian Proksch, Sarah Nadi, Mira Mezini

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Intelligent code completion recommends relevant code to de- velopers by comparing the editor content to code patterns extracted by analyzing large repositories. However, with the vast amount of data available in such repositories, scalability of the recommender system becomes an issue. We propose using Boolean Matrix Factorization (BMF) as a clustering technique for analyzing code in order to improve scalability of the underlying models. We compare model size, inference speed, and prediction quality of an intelligent method call completion engine built on top of canopy clustering versus one built on top of BMF. Our results show that BMF reduces model size up to 80% and increases inference speed up to 78%, without signifficant change in prediction quality.

Original languageEnglish (US)
Title of host publicationSWAN 2016 - Proceedings of the 2nd International Workshop on Software Analytics, co-located with FSE 2016
EditorsLatifa Guerrouj, David Lo, Olga Baysal, Jacek Czerwonka, Brendan Murphy
PublisherAssociation for Computing Machinery, Inc
Pages1-7
Number of pages7
ISBN (Electronic)9781450343954
DOIs
StatePublished - Nov 13 2016
Event2nd International Workshop on Software Analytics, SWAN 2016 - Seattle, United States
Duration: Nov 13 2016 → …

Publication series

NameSWAN 2016 - Proceedings of the 2nd International Workshop on Software Analytics, co-located with FSE 2016

Conference

Conference2nd International Workshop on Software Analytics, SWAN 2016
Country/TerritoryUnited States
CitySeattle
Period11/13/16 → …

Keywords

  • Analytics of code repositories
  • Boolean Matrix Factorization
  • Intelligent method call completion
  • Scalability

ASJC Scopus subject areas

  • Software
  • Information Systems

Fingerprint

Dive into the research topics of 'Addressing scalability in API method call analytics'. Together they form a unique fingerprint.

Cite this