VAPER: A deep learning model for explainable probabilistic regression

Seungwon Jung, Yoona Noh, Jaeuk Moon, Eenjun Hwang

Abstract: Highlights•We propose a novel deep learning model based on VAE and LRP for explainable probabilistic regression.•We show that the proposed model has competitive regression performance and supports the explainability of the result.•We describe in detail the results of relevance interpretation for predicted house prices using the well-known Boston dataset.