TY - GEN
T1 - Predictability classification for software effort estimation
AU - Kinoshita, Naoki
AU - Monden, Akito
AU - Tshunoda, Masateru
AU - Yucel, Zeynep
N1 - Funding Information:
This research was supported by JSPS KAKENHI Grant number 17K00102.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/11/9
Y1 - 2018/11/9
N2 - In this paper, focusing on the problem that estimation accuracy of software development effort greatly varies among software projects, we propose a predictability classification method for software projects before conducting effort estimation. In the proposed method, given a project to be estimated, we first evaluate whether the effort can be accurately estimated or not by identifying the project as 'predictable' or 'unpredictable'. In case of predictable projects, we conduct the effort estimation. Otherwise, estimation is avoided. As a result of an experiment to assess the effectiveness of the proposed method using six industry datasets, (i) the mean square residual and residual variance are shown to be suitable measures for recognition of predictability; and (ii) the average absolute error is significantly reduced in five datasets, by avoiding the estimation when a project belongs to the unpredictable class, which proves the effectiveness of the proposed method. By using the proposed method, practitioners become aware of cases when they can rely on the estimation and when they cannot.
AB - In this paper, focusing on the problem that estimation accuracy of software development effort greatly varies among software projects, we propose a predictability classification method for software projects before conducting effort estimation. In the proposed method, given a project to be estimated, we first evaluate whether the effort can be accurately estimated or not by identifying the project as 'predictable' or 'unpredictable'. In case of predictable projects, we conduct the effort estimation. Otherwise, estimation is avoided. As a result of an experiment to assess the effectiveness of the proposed method using six industry datasets, (i) the mean square residual and residual variance are shown to be suitable measures for recognition of predictability; and (ii) the average absolute error is significantly reduced in five datasets, by avoiding the estimation when a project belongs to the unpredictable class, which proves the effectiveness of the proposed method. By using the proposed method, practitioners become aware of cases when they can rely on the estimation and when they cannot.
KW - Data-mining
KW - Empirical-study
KW - Multivariate-regression
KW - Software-effort-estimation
KW - Software-project-management
UR - http://www.scopus.com/inward/record.url?scp=85058492809&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85058492809&partnerID=8YFLogxK
U2 - 10.1109/BCD2018.2018.00015
DO - 10.1109/BCD2018.2018.00015
M3 - Conference contribution
AN - SCOPUS:85058492809
T3 - Proceedings - 2018 IEEE/ACIS 3rd International Conference on Big Data, Cloud Computing, Data Science and Engineering, BCD 2018
SP - 43
EP - 48
BT - Proceedings - 2018 IEEE/ACIS 3rd International Conference on Big Data, Cloud Computing, Data Science and Engineering, BCD 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd IEEE/ACIS International Conference on Big Data, Cloud Computing, Data Science and Engineering, BCD 2018
Y2 - 10 July 2018 through 12 July 2018
ER -