公开(公告)号：US20190303716A1

公开(公告)日：2019-10-03

申请号：US15938624

申请日：2018-03-28

Applicant: ENTIT Software LLC

Inventor： Manish Marwah ,  Xiao Zhang ,  Martin Arlitt

IPC: G06K9/62 ,  G06F17/18 ,  G06F17/17 ,  G06F15/18

Abstract: Points around a point of interest are sampled. The points and the point of interest each have a value for each of a number of input features. The points and the point of interest each have a corresponding output score for a machine learning model. A feature contribution vector for the input features is determined by locally approximating the machine learning model at the points and the point of interest using a model, such as a ridge regression model. The ridge regression model can have a loss function, which can include a Kullback-Leibler (KL) divergence term. The feature contribution vector approximates for any point a contribution of each input feature to the output score of this point by the machine learning model. The input features most responsible for the machine learning model having provided the corresponding output score for the point of interest, based on the feature contribution vector, are provided.