- author = "Federica Sarro and Alessio Petrozziello and Mark Harman",
- title = "Multi-objective Software Effort Estimation",
- booktitle = "Proceedings of the 38th International Conference on Software Engineering, ICSE '16",
- year = "2016",
- pages = "619--630",
- address = "Austin, Texas, USA",
- publisher_address = "New York, NY, USA",
- publisher = "ACM",
- note = "Humie 2016 Bronze Medal",
- keywords = "genetic algorithms, genetic programming, SBSE, NSGA-II, confidence interval, estimates uncertainty, multi-objective evolutionary algorithm, software effort estimation",
- isbn13 = "978-1-4503-3900-1",
- acmid = "2884830",
-
URL = "
http://www.cs.ucl.ac.uk/staff/F.Sarro/resource/papers/SarroICSE2016.pdf",
-
URL = "
http://doi.acm.org/10.1145/2884781.2884830",
-
DOI = "
doi:10.1145/2884781.2884830",
- size = "12",
- abstract = "We introduce a bi-objective effort estimation algorithm that combines Confidence Interval Analysis and assessment of Mean Absolute Error. We evaluate our proposed algorithm on three different alternative formulations, baseline comparators and current state-of-the-art effort estimators applied to five real-world datasets from the PROMISE repository, involving 724 different software projects in total. The results reveal that our algorithm outperforms the baseline, state-of-the-art and all three alternative formulations, statistically significantly and with large effect size over all five datasets. We also provide evidence that our algorithm creates a new state-of-the-art, which lies within currently claimed industrial human-expert-based thresholds, thereby demonstrating that our findings have actionable conclusions for practising software engineers.",
-
notes = "Linear genome
Also known as \cite{Sarro:2016:MSE:2884781.2884830}",
