Mathematics · 2023 · 19 citations · 17 references
ComputingComputer ScienceInsuranceActuarial ScienceArtificial IntelligenceMachine LearningExplainable Machine LearningInsurance RiskRisk ClassificationExplainabilityExplainability MetricsExplainability Of Insurance AlgorithmsExplainable Artificial IntelligenceMachine Learning For InsuranceMachine Learning Prediction ModelsMean Absolute ErrorMean Absolute Error Analysis
Machine learning, a subfield of artificial intelligence, emphasizes the creation of algorithms capable of learning from data and generating predictions. However, in actuarial science, the interpretability of these models often presents challenges, raising concerns about their accuracy and reliability. Explainable artificial intelligence (XAI) has emerged to address these issues by facilitating the development of accurate and comprehensible models. This paper conducts a comparative analysis of various XAI approaches for tackling distinct data-driven insurance problems. The machine learning methods are evaluated based on their accuracy, employing the mean absolute error for regression problems and the accuracy metric for classification problems. Moreover, the interpretability of these methods is assessed through quantitative and qualitative measures of the explanations offered by each explainability technique. The findings reveal that the performance of different XAI methods varies depending on the particular insurance problem at hand. Our research underscores the significance of considering accuracy and interpretability when selecting a machine-learning approach for resolving data-driven insurance challenges. By developing accurate and comprehensible models, we can enhance the transparency and trustworthiness of the predictions generated by these models.
17
Marco Túlio Ribeiro, Sameer Singh, Carlos Guestrin · 2016 · 15.2K citations
From local explanations to global understanding with explainable AI for trees
Scott Lundberg, Gabriel Erion, Hugh Chen et al. · Nature Machine Intelligence · 2020 · 8.9K citations · Full text
On the Tractability of SHAP Explanations
Guy Van den Broeck, Anton Lykov, Maximilian Schleich et al. · Journal of Artificial Intelligence Research · 2022 · 437 citations · Full text
Variable Importance Plots—An Introduction to the vip Package
M. Greenwell Brandon, C. Boehmke Bradley · The R Journal · 2020 · 339 citations · Full text
Computing, Data Science, Data Mining +14