Abstract:
While significant research has been conducted on
software analytics for effort estimation in traditional software
projects, limited attention has been given to estimation in agile
projects, particularly in estimating the effort required for
completing user stories. In our study, we present a novel
prediction model for estimating story points, which serves as a
common unit of measure for gauging the effort involved in
completing a user story or resolving an issue. To achieve this, we
propose a unique combination of two powerful deep learning
architectures, namely LSTM and RHN. What sets our prediction
system apart is its end-to-end training capability, allowing it to
learn directly from raw input data without relying on manual
feature engineering. To support our research, we have curated a
comprehensive dataset specifically tailored for story points-based
estimation. This dataset comprises 6801 issues extracted from 6
different open-source projects. Through an empirical evaluation,
we demonstrate the superiority of our approach over three
common baselines. In summary, our study addresses the gap in
research regarding agile project estimation by introducing a
prediction model that effectively estimates story points. By
leveraging the combined power of LSTM and RHN architectures.