Wells Fargo Bank, N.a.

Kevin D Oden

Agus Sudjianto

Jie Chen

Vijayan Narayana Nair

John V Hintze

Weicheng Liu

Casey A Bennett

Tapan Shah

Jason Hilliard

Steve Cardinale

Simon Cann

The innovation disclosed and claimed herein, in one aspect thereof, comprises systems and methods of validating models guided by machine learning algorithms. The innovation can begin by receiving a risk model for validation having multiple sets of data. A first data set is selected from as an input. Outputs are generated for validation. One output can be generating a second set of analysis results using a comparable algorithm to the risk model. Another output can be generating a second set of variables and transformations using a machine learning algorithm and an untransformed set of the selected variables to assess the set of selected transformations. Another output can be generating a third set of variables using one or more machine learning algorithms and an extended feature set of variables to assess the selected variables. The outputs are compared to the analysis results, coefficients, selected variables, and selected transformations. A report of the comparison is generated.

Model validation of credit risk

A model management system receives data for an inventory of models including data regarding issues for each of the models. The model management system determines a model risk score for each of the models based on the issues for each of the models. As the issues are opened and closed, the model management system receives updates and in real-time, updates the model risk score. The model risk score can be determined using a severity assigned to each issue for each of the open issues for a given model as well as the number of issues at each severity. Risk scores can be calculated across a line of business and across an enterprise, for example. The model management system also provides one or more of: model development, model validation, model integration, model use, model maintenance, and model retirement.

Model management system

The innovation disclosed and claimed herein, in one aspect thereof, comprises systems and methods of validating models guided by machine learning algorithms. The innovation can begin by receiving a risk model for validation having multiple sets of data. A first data set is selected from as an input. Outputs are generated for validation. One output can be generating a second set of analysis results using a comparable algorithm to the risk model. Another output can be generating a second set of variables and transformations using a machine learning algorithm and an un-transformed set of the selected variables to assess the set of selected transformations. Another output can be generating a third set of variables using one or more machine learning algorithms and an extended feature set of variables to assess the selected variables. The outputs are compared to the analysis results, coefficients, selected variables, and selected transformations. A report of the comparison is generated.

Growing community of inventors

Charlotte, NC, United States of America

Kevin D Oden