Skip to main content
placeholder image

Explainable software analytics

Conference Paper


Download full-text (Open Access)

Abstract


  • © 2018 Association for Computing Machinery. Software analytics has been the subject of considerable recent attention but is yet to receive significant industry traction. One of the key reasons is that software practitioners are reluctant to trust predictions produced by the analytics machinery without understanding the rationale for those predictions. While complex models such as deep learning and ensemble methods improve predictive performance, they have limited explainability. In this paper, we argue that making software analytics models explainable to software practitioners is as important as achieving accurate predictions. Explainability should therefore be a key measure for evaluating software analytics models.We envision that explainability will be a key driver for developing software analytics models that are useful in practice. We outline a research roadmap for this space, building on social science, explainable artificial intelligence and software engineering.

Publication Date


  • 2018

Citation


  • Dam, H., Tran, T. & Ghose, A. (2018). Explainable software analytics. International Conference on Software Engineering 2018 (pp. 53-56). AIS Digital Library.

Scopus Eid


  • 2-s2.0-85049803254

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=2671&context=eispapers1

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/1669

Start Page


  • 53

End Page


  • 56

Abstract


  • © 2018 Association for Computing Machinery. Software analytics has been the subject of considerable recent attention but is yet to receive significant industry traction. One of the key reasons is that software practitioners are reluctant to trust predictions produced by the analytics machinery without understanding the rationale for those predictions. While complex models such as deep learning and ensemble methods improve predictive performance, they have limited explainability. In this paper, we argue that making software analytics models explainable to software practitioners is as important as achieving accurate predictions. Explainability should therefore be a key measure for evaluating software analytics models.We envision that explainability will be a key driver for developing software analytics models that are useful in practice. We outline a research roadmap for this space, building on social science, explainable artificial intelligence and software engineering.

Publication Date


  • 2018

Citation


  • Dam, H., Tran, T. & Ghose, A. (2018). Explainable software analytics. International Conference on Software Engineering 2018 (pp. 53-56). AIS Digital Library.

Scopus Eid


  • 2-s2.0-85049803254

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=2671&context=eispapers1

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/1669

Start Page


  • 53

End Page


  • 56