UCLIC Research Seminar Series

Engaging end user groups with machine learning (ML) models can help align the design of predictive systems with people's needs and expectations. In this talk, I will present a co-design study [1] investigating the benefits and challenges of using computational notebooks to inform ML models with end user groups. We used computational notebooks to engage young adults, carers, and clinicians with an example ML model that predicted health risk in diabetes care. Through co-design workshops and retrospective interviews, we found that participants particularly valued using the interactive data visualisations of the computational notebooks to scaffold multidisciplinary learning, anticipate benefits and harms of the example ML model, and create fictional feature importance plots to highlight care needs. Participants also reported challenges, from running code cells to managing information asymmetries and power imbalances. Based on this understanding, I will discuss the potential of leveraging interactive technologies, such as computational notebooks, as co-design tools to meet end user needs early in ML model lifecycles.

[1] Amid Ayobi, Jacob Hughes, Christopher J Duckworth, Jakub J Dylag, Sam James, Paul Marshall, Matthew Guy, Anitha Kumaran, Adriane Chapman, Michael Boniface, and Aisling Ann O'Kane. 2023. Computational Notebooks as Co-Design Tools: Engaging Young Adults Living with Diabetes, Family Carers, and Clinicians with Machine Learning Models. CHI'23, Preprint: discovery.ucl.ac.uk/id/eprint/10166134