No Ground Truth at Sea - Developing High-Accuracy AI Decision-Support for Complex Environments
Paper i proceeding, 2023

As AI decision-support systems are increasingly developed for applications outside of traditional organizational confinements, developers are confronted with new sources of complexity they need to address. However, we know little about how AI applications are developed for natural use domains with high environmental complexity, stemming from physical influences outside of the developers' control. This study investigates what challenges emerge from such complexity and how developers mitigate them. Drawing upon a rich longitudinal single-case study on the development of AI decision-support for maritime navigation, findings show that achieving high output accuracy is complicated by the physical environment hindering training data creation. Further, developers chose to reduce the output accuracy and adapt the HMI design to successfully situate the AI application in an existing sociotechnical context. This study contributes to IS literature following recent calls for phenomenon-based examination of emerging challenges when extending the scope frontier of AI and provides practical recommendations for developing AI decision-support for complex environments.

AI decision-support

complexity

AI development

maritime navigation

case study

Författare

Adrian Bumann

Chalmers, Teknikens ekonomi och organisation, Entrepreneurship and Strategy

Proceedings of the Annual Hawaii International Conference on System Sciences

15301605 (ISSN)

Vol. 2023-January 4566-4575
9780998133164 (ISBN)

56th Annual Hawaii International Conference on System Sciences, HICSS 2023
Virtual, Online, USA,

Ämneskategorier

Övrig annan teknik

Programvaruteknik

Systemvetenskap, informationssystem och informatik med samhällsvetenskaplig inriktning

Mer information

Senast uppdaterat

2024-01-03