SAP SE
Explainable Machine Learning Predictions

Abstract:

Systems, methods, and computer products are described herein for explainable machined learning predictions. An application receives data including a specification that defines a trained machine learning (ML) model. The application parses a model description of the trained ML model. An engine factory creates an instance of an engine based on the model description. The application generates an user interface (UI) for requesting a prediction and an associated explanation using the engine. The UI receives user input data including a requested prediction having one or more influencers. The engine determines and provides the prediction and the associated explanation based on the user input data.