Contextualising local explanations for non-expert users: an XAI pricing interface for insurance

Clara Bove (1, 2) , Jonathan Aigrain (1) , Marie-Jeanne Lesot (2) , Charles Tijus (3, 4) , Marcin Detyniecki (1)

1 AXA - Groupe AXA
2 LFI - Learning, Fuzzy and Intelligent systems
3 LUTIN - Laboratoire des Usages en Technologies d'Information Numériques
4 UP8 - Université Paris 8 Vincennes-Saint-Denis

Machine Learning has provided new business opportunities in the insurance industry, but its adoption is for now limited by the difficulty to explain the rationale behind the prediction provided. In this work, we explore how we can enhance local feature importance explanations for non-expert users. We propose design principles to contextualise these explanations with additional information about the Machine Learning system, the domain and external factors that may influence the prediction. These principles are applied to a car insurance smart pricing interface. We present preliminary observations collected during a pilot study using an online A/B test to measure objective understanding, perceived understanding and perceived usefulness of explanations. The preliminary results are encouraging as they hint that providing contextualisation elements can improve the understanding of ML predictions.

Mots clés: Artificial Intelligence; Trust; Human Computer Interaction; Artificial Conversational Agent; Design Guidelines; Interaction design; Interpretability; Explainability; Interface Principle; Interaction Human-ML; Machine Learning; Contextualisation; Explanations

Domaines: Interface homme-machine [cs.HC]; Intelligence artificielle [cs.AI]; Informatique

Clara Bove, Jonathan Aigrain, Marie-Jeanne Lesot, Charles Tijus, Marcin Detyniecki. Contextualising local explanations for non-expert users: an XAI pricing interface for insurance. Joint Proceedings of the ACM IUI 2021 Workshops, Apr 2021, College Station, United States. ⟨hal-03844389⟩