Presentation 2005-10-13
A Comparison of Effort Prediction Methods Using Similar Projects
Masateru TSUNODA, Takeshi KAKIMOTO, Naoki OHSUGI, Akito MONDEN, Kenichi MATSUMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Due to heterogeneity of recent software development organizations and software processes, a single effort prediction model, such as COCOMO and regression models, often does not perform well to predict an individual project. On the other hand, effort prediction methods based on project similarity (Case-Based Reasoning (CBR) and Collaborative Filtering (CF)) have become an attractive alternatives in recent years because they consider individuality of each project in prediction. However, there are no empirical evaluation conducted to compare CBR and CF. Therefore, we focus on these methods and compared their prediction performance using real project data. The result showed that CF showed better prediction performance than CBR.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) missing value / collaborative filtering / case-based reasoning / cost estimation / project management
Paper # SS2005-47
Date of Issue

Conference Information
Committee SS
Conference Date 2005/10/6(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Software Science (SS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Comparison of Effort Prediction Methods Using Similar Projects
Sub Title (in English)
Keyword(1) missing value
Keyword(2) collaborative filtering
Keyword(3) case-based reasoning
Keyword(4) cost estimation
Keyword(5) project management
1st Author's Name Masateru TSUNODA
1st Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology Kansai Science City()
2nd Author's Name Takeshi KAKIMOTO
2nd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology Kansai Science City
3rd Author's Name Naoki OHSUGI
3rd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology Kansai Science City
4th Author's Name Akito MONDEN
4th Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology Kansai Science City
5th Author's Name Kenichi MATSUMOTO
5th Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology Kansai Science City
Date 2005-10-13
Paper # SS2005-47
Volume (vol) vol.105
Number (no) 331
Page pp.pp.-
#Pages 6
Date of Issue