Generally, the present disclosure is directed to systems and methods that enable explanation of personalized machine-learned model outputs. For example, the systems and methods of the present disclosure can include or leverage a user interface and/or an application programming interface (API) to enable explanation of model outputs. According to one aspect, the present disclosure provides a principled way of discovering which actions or range of actions that the user took contributed to a particular output that the model predicted at later time. This allows, for example, an application that employs the personalized model to describe to the user which actions contributed most likely to the model’s prediction.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
N/A, "User Interface and Application Programming Interface for Explaining Personalized Machine-Learned Model Outputs", Technical Disclosure Commons, (December 12, 2017)