Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Evaluation of memory based collaborative filtering for repository recommendation on Github
KTH, School of Computer Science and Communication (CSC).
2017 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Utvärdering av minnesbaserad kollaborativ rekommendation av Github-projekt (Swedish)
Abstract [en]

GitHub is host to a huge number of repositories. In order to explore and find new and interesting repositories on GitHub users has to rely on global charts or explore manually. Recommender systems are a type of software algorithms that produce personalized recommendations to users. One class of such algorithms are called memory based collaborative filtering. This report explore whether this kind of algorithms can be used to generate personalized recommendations of repositories on GitHub to its users, which is achieved by evaluating existing methods of generating predictions using memory based collaborative filtering which is then implemented for experimentation. The results indicates that memory based collaborative filtering might be a slightly better choice than global charts for a small percentage of the users, but for most users it is not.

Abstract [sv]

Det finns en väldigt stor mängd git-project tillgängliga på GitHub. Om en användare vill upptäcka intressanta projekt måste denne förlita sig på allmänna topplistor alternativt utforska GitHub på egen hand. Rekommendationssystem är en slags mjukvaru algoritmer som kan skapa personligt anpassade rekommendationer till användare. En speciell typ av dessa algoritmer kallas för minnesbaserad kollaborativ rekommendation. Den här avhandlingen ämnar utforska huruvida denna typ av algoritmer kan användas för att rekommendera git-projekt till användare på GitHub. Detta görs genom att utvärdera relevant forskning i området vilket leder till en rad experiment vilka utverderar tillförlitlheten hos ett antal algoritmer. Resultaten från dessa experiment indikerar att minnesbaserad kollaborativ rekommendation är något bättre än allmänna topplistor för en liten grupp av användare på GitHub. För de allra flesta är dock allmänna topplistor ett bättre alternativ.

Place, publisher, year, edition, pages
2017.
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-208389OAI: oai:DiVA.org:kth-208389DiVA, id: diva2:1105995
Supervisors
Examiners
Available from: 2017-06-19 Created: 2017-06-06 Last updated: 2018-01-13Bibliographically approved

Open Access in DiVA

fulltext(741 kB)159 downloads
File information
File name FULLTEXT01.pdfFile size 741 kBChecksum SHA-512
a64d103420d3659d27e618c1dc47872c73da48499c66d623afde383fc6b4aa235efbe59a31f8ac667a0877bf17a4aaac016b19a152293743ce499c59598f7f10
Type fulltextMimetype application/pdf

By organisation
School of Computer Science and Communication (CSC)
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 159 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 196 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf