Explaining single predictions : a faster method
Machine learning has proven increasingly essential in manyfields. Yet, a lot obstacles still hinder its use by non-experts. The lack oftrust in the results obtained is foremost among them, and has inspiredseveral explanatory approaches in the literature. In this paper, we areinvestigating the domain of single prediction explanation.
This is per-formed by providing the user a detailed explanation of the attribute’sinfluence on each single predicted instance, related to a particular ma-chine learning model. A lot of possible explanation methods have beendeveloped recently.
Although, these approaches often require an impor-tant computation time in order to be efficient. That is why we are inves-tigating about new proposals of explanation methods, aiming to increasetime performances, for a small loss in accuracy.