Intuit, Inc.

Eric King Loong Shiu

Wei W Wang

Alexander S Ran

Christopher Z Lesner

Marko Rukonic

Zhicheng Xue

Certain aspects of the present disclosure provide techniques for generating a human readable summary explanation to a user for an outcome generated by a complex machine learning model. In one embodiment, a risk assessment service can receive a request from a user in which a risk model of the risk assessment service performs a specific task (e.g., determining the level of risk associated with the user). Once the risk model determines the risk associated with the user, in order to comply with regulations from a compliance system, the risk model can provide a user with an explanation as to the outcome for transparency purposes.

Explainable complex model

A method may include obtaining unpaired transactions each including a transaction ID, an entity ID, and attributes that each correspond to an attribute type, deriving transaction groups by grouping the unpaired transactions using their entity IDs, and dividing a transaction group into a first transaction subgroup and a second transaction subgroup. The method may further include constructing a tree for the first transaction subgroup based on an attribute type, and matching a first transaction of the first transaction subgroup with a second transaction of the second transaction subgroup by searching the tree while applying a matching criterion to the transactions of the second transaction subgroup. The matching criterion may correspond to the attribute type. The method may further include: forming a matched transfer pair including the entity ID of the transaction group, the transaction ID of the first transaction, and the transaction ID of the second transaction.

Growing community of inventors

Milpitas, CA, United States of America

Eric King Loong Shiu