Thu 8 Nov 2018 11:15 - 11:37 at Horizons 5 - Estimation and Prediction Chair(s): Jim Herbsleb

\textbf{Background:} software effort estimation (SEE) usually suffers from data scarcity problem due to the expensive or long process of data collection. As a result, companies usually have limited data projects for effort estimation, causing unsatisfactory prediction performance. Few studies have investigated strategies to generate additional SEE data to aid such learning.
\textbf{Aim:} to propose a synthetic data generator to address the data scarcity problem of SEE. The proposed approach should be general to be used with any state-of-the-art SEE method. Ideally, it should be simple and hardly have negative effect on SEE performance.
\textbf{Method:} our synthetic generator enlarges the SEE data set size by slightly displacing some randomly chosen training examples. It can be used with any SEE method as a data preprocessor.
Its effectiveness is justified with 6 state-of-the-art SEE models across 14 SEE data sets. We also compare our data generator against the only existing approach in the SEE literature.
\textbf{Results:} our synthetic projects can significantly improve the performance of some SEE methods especially when the training data is insufficient. When they cannot significantly improve the prediction performance, they are not detrimental either.
Besides, our synthetic data generator is significantly superior or perform similarly to its competitor in the SEE literature.
\textbf{Conclusion:} our data generator plays a non-harmful if not significantly beneficial effect on the SEE methods investigated in this paper. Therefore, it is helpful in addressing the data scarcity problem of SEE.

Thu 8 Nov
Times are displayed in time zone: (GMT-05:00) Guadalajara, Mexico City, Monterrey change

10:30 - 12:00: Research Papers - Estimation and Prediction at Horizons 5
Chair(s): Jim HerbslebCarnegie Mellon University
fse-2018-Journal-First10:30 - 10:52
Yuanrui Fan, Xin XiaMonash University, David LoSingapore Management University, Shanping Li
fse-2018-Journal-First10:52 - 11:15
Yuming Zhou, Yibiao YangNanjing University, China, Hongmin Lu, Lin ChenNanjing University, Yanhui Li, Yangyang Zhao, Junyan Qian, Baowen Xu
Link to publication DOI
fse-2018-research-papers11:15 - 11:37
fse-2018-research-papers11:37 - 12:00
Qingwei LinMicrosoft, China, Ken Hsieh, Yingnong DangMicrosoft, USA, Hongyu ZhangThe University of Newcastle, Kaixin SuiMicrosoft, China, Yong XuMicrosoft, China, Jian-Guang LouMicrosoft Research, Chenggang LiNortheastern University, China, Youjiang WuMicrosoft, USA, Randolph YaoMicrosoft, USA, Murali ChintalapatiMicrosoft, USA, Dongmei ZhangMicrosoft Research, China