Kjersti Aas

Latest

• Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features
• Exabel's Factor Model
• Performance evaluation of volatility estimation methods for Exabel
• Efficient and simple prediction explanations with groupShapley -- A practical perspective
• Efficient and simple prediction explanations with groupShapley: A practical perspective
• Explaining individual predictions when features are dependent: More accurate approximations to Shapley values
• Explaining predictive models using Shapley values and non-parametric vine copulas
• groupShapley: Efficient prediction explanation with Shapley values for feature groups
• MCCE: Monte Carlo sampling of realistic counterfactual explanations
• Explaining predictive models with mixed features using Shapley values and conditional inference trees