Explanation Generation Mechanism for Black Box Recommendation Model

Abstract

The recommender system is everywhere, and even streaming platform they have been looking for a maze of user available information handling products and services. Unfortunately, these black box systems do not have sufficient transparency, as they provide littlie description about the their prediction. In contrast, the white box system by its nature can produce a brief description. However, their predictions are less accurate than complex black box models. Recent research has shown that explanations are an important component in bringing powerful big data predictions and machine learning techniques to a mass audience without compromising trust.This paper proposes a new approach using semantic web technology to generate an explanation for the output of a black box recommender system. The developed model is trained to make predictions accompanied by explanations that are automatically extracted from the semantic network.