TY - JOUR
T1 - Towards Accountability Driven Development for Machine Learning Systems
AU - Fung, Chiu Pang
AU - Pang, Wei
AU - Naja, Iman
AU - Markovic, Milan
AU - Edwards, Peter
N1 - Funding Information:
★This research is supported by the RAInS project funded by EPSRC (EP/R033846/1). Corresponding Author: Wei Pang ([email protected]) Copyright © 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Publisher Copyright:
Copyright © 2021 for this paper by its authors.
PY - 2021/7/2
Y1 - 2021/7/2
N2 - With rapid deployment of Machine Learning (ML) systems into diverse domains such as healthcare and autonomous driving, important questions regarding accountability in case of incidents resulting from ML errors remain largely unsolved. To improve accountability of ML systems, we introduce a framework called Accountability Driven Development (ADD). Our framework reuses Behaviour Driven Development (BDD) approach to describe testing scenarios and system behaviours in ML Systems’ development using natural language, guides and forces developers and intended users to actively record necessary accountability information in the design and implementation stages. In this paper, we illustrate how to transform accountability requirements to specific scenarios and provide syntax to describe them. The use of natural language allows non technical collaborators such as stakeholders and non ML domain experts deeply engaged in ML system development to provide more comprehensive evidence to support system’s accountability. This framework also attributes the responsibility to the whole project team including the intended users rather than putting all the accountability burden on ML engineers only. Moreover, this framework can be considered as a combination of both system test and acceptance test, thus making the development more efficient. We hope this work can attract more engineers to use our idea, which enables them to create more accountable ML systems.
AB - With rapid deployment of Machine Learning (ML) systems into diverse domains such as healthcare and autonomous driving, important questions regarding accountability in case of incidents resulting from ML errors remain largely unsolved. To improve accountability of ML systems, we introduce a framework called Accountability Driven Development (ADD). Our framework reuses Behaviour Driven Development (BDD) approach to describe testing scenarios and system behaviours in ML Systems’ development using natural language, guides and forces developers and intended users to actively record necessary accountability information in the design and implementation stages. In this paper, we illustrate how to transform accountability requirements to specific scenarios and provide syntax to describe them. The use of natural language allows non technical collaborators such as stakeholders and non ML domain experts deeply engaged in ML system development to provide more comprehensive evidence to support system’s accountability. This framework also attributes the responsibility to the whole project team including the intended users rather than putting all the accountability burden on ML engineers only. Moreover, this framework can be considered as a combination of both system test and acceptance test, thus making the development more efficient. We hope this work can attract more engineers to use our idea, which enables them to create more accountable ML systems.
KW - Accountability
KW - Behaviour driven development
KW - Machine learning
KW - Model card
UR - http://www.scopus.com/inward/record.url?scp=85109637089&partnerID=8YFLogxK
M3 - Conference article
SN - 1613-0073
VL - 2894
SP - 25
EP - 32
JO - CEUR Workshop Proceedings
JF - CEUR Workshop Proceedings
T2 - SICSA Workshop on eXplainable Artificial Intelligence 2021
Y2 - 1 June 2021 through 1 June 2021
ER -