Abstract: A system and method includes obtaining an incumbent model and a candidate model, generating a plurality of synthetic model input datasets, computing, for each synthetic model input dataset, a model performance efficacy metric and a model fairness efficacy metric for the incumbent model based on assessing model output data of the incumbent model that corresponds to each respective synthetic model input dataset of the plurality of synthetic model input datasets, computing, for each synthetic model input dataset, a model performance efficacy metric and a model fairness efficacy metric for the candidate model based on assessing model output data of the candidate model that corresponds to each respective synthetic model input dataset of the plurality of synthetic model input datasets, computing, for the candidate model, a disparity-mitigating model viability score, and displaying, via a graphical user interface, a representation of the candidate model in association with the disparity-mitigating model viability sc

Abstract: A system and method includes obtaining an incumbent model and a candidate model, generating a plurality of synthetic model input datasets, computing, for each synthetic model input dataset, a model performance efficacy metric and a model fairness efficacy metric for the incumbent model based on assessing model output data of the incumbent model that corresponds to each respective synthetic model input dataset of the plurality of synthetic model input datasets, computing, for each synthetic model input dataset, a model performance efficacy metric and a model fairness efficacy metric for the candidate model based on assessing model output data of the candidate model that corresponds to each respective synthetic model input dataset of the plurality of synthetic model input datasets, computing, for the candidate model, a disparity-mitigating model viability score, and displaying, via a graphical user interface, a representation of the candidate model in association with the disparity-mitigating model viability sc

Abstract: Systems and methods for training models to improve fairness.

Abstract: Methods, non-transitory computer readable media, and model evaluations systems for understanding diverse machine learning models (MLMs) are disclosed. In some examples, a feature contribution value is determined for features included in a reference or evaluation input data set. The evaluation input data set represents a protected class population and each feature contribution value identifies a contribution by a feature to a difference in output generated by an MLM for the evaluation input data set. Model explanation information is generated using the feature contribution values and execution of the MLM is monitored. The model explanation information explains the difference in output generated by the MLM for the evaluation input data set and includes information relating to a model-based decision. A report is generated from a knowledge graph for the MLM and output via a GUI to an operator device that includes the model explanation information.

Abstract: A system and method includes generating approximate distributions for distinct classes of data samples; computing a first partial Jensen-Shannon (JS) divergence and a second partial JS divergence based on the approximate distribution of the disparity affected class of data samples with reference to the approximate distribution of the control class of data samples; computing a disparity divergence based on the first partial JS divergence and the second partial JS divergence; generating a distribution-matching term based on the disparity divergence, wherein the distribution-matching term mitigates an inferential disparity between the control class of data samples and the disparity affected class of data samples during a training of an unconstrained artificial neural network; constructing a disparity-constrained loss function based on augmenting a target loss function with the distribution-matching term; and transforming the unconstrained ANN to a disparity-constrained ANN based on a training of the unconstraine

Abstract: A system and method includes generating approximate distributions for distinct classes of data samples; computing a first partial Jensen-Shannon (JS) divergence and a second partial JS divergence based on the approximate distribution of the disparity affected class of data samples with reference to the approximate distribution of the control class of data samples; computing a disparity divergence based on the first partial JS divergence and the second partial JS divergence; generating a distribution-matching term based on the disparity divergence, wherein the distribution-matching term mitigates an inferential disparity between the control class of data samples and the disparity affected class of data samples during a training of an unconstrained artificial neural network; constructing a disparity-constrained loss function based on augmenting a target loss function with the distribution-matching term; and transforming the unconstrained ANN to a disparity-constrained ANN based on a training of the unconstraine

Abstract: Systems and methods for training models to improve fairness.

Abstract: A system and method includes generating approximate distributions for distinct classes of data samples; computing a first partial Jensen-Shannon (JS) divergence and a second partial JS divergence based on the approximate distribution of the disparity affected class of data samples with reference to the approximate distribution of the control class of data samples; computing a disparity divergence based on the first partial JS divergence and the second partial JS divergence; generating a distribution-matching term based on the disparity divergence, wherein the distribution-matching term mitigates an inferential disparity between the control class of data samples and the disparity affected class of data samples during a training of an unconstrained artificial neural network; constructing a disparity-constrained loss function based on augmenting a target loss function with the distribution-matching term; and transforming the unconstrained ANN to a disparity-constrained ANN based on a training of the unconstraine

Abstract: Systems and methods for generating and processing modeling workflows are disclosed. In some examples, a reference distribution of scores generated by a model is determined. The reference distribution of scores is recorded in a structured database. One or more unexpected scores are detected during execution of the model. To detect the one or more unexpected scores, a production distribution of scores is compared with the reference distribution of scores recorded in the structured database. The production distribution of scores is generated by the model for a production input data set. An alert is then provided to an external system, when an alert condition is determined to be satisfied based on the comparison. The alert indicates detection of the one or more unexpected scores.

Abstract: Methods, non-transitory computer readable media, and model evaluations systems for understanding diverse machine learning models (MLMs) are disclosed. In some examples, a feature contribution value is determined for features included in a reference or evaluation input data set. The evaluation input data set represents a protected class population and each feature contribution value identifies a contribution by a feature to a difference in output generated by an MLM for the evaluation input data set. Model explanation information is generated using the feature contribution values and execution of the MLM is monitored. The model explanation information explains the difference in output generated by the MLM for the evaluation input data set and includes information relating to a model-based decision. A report is generated from a knowledge graph for the MLM and output via a GUI to an operator device that includes the model explanation information.

Abstract: Systems and methods for training models to improve fairness.

Abstract: Systems and methods for generating and processing modeling workflows.

Abstract: Systems and methods for understanding diverse machine learning models.

Abstract: A system and method includes generating approximate distributions for distinct classes of data samples; computing a first partial Jensen-Shannon (JS) divergence and a second partial JS divergence based on the approximate distribution of the disparity affected class of data samples with reference to the approximate distribution of the control class of data samples; computing a disparity divergence based on the first partial JS divergence and the second partial JS divergence; generating a distribution-matching term based on the disparity divergence, wherein the distribution-matching term mitigates an inferential disparity between the control class of data samples and the disparity affected class of data samples during a training of an unconstrained artificial neural network; constructing a disparity-constrained loss function based on augmenting a target loss function with the distribution-matching term; and transforming the unconstrained ANN to a disparity-constrained ANN based on a training of the unconstraine

Abstract: A system and method includes generating approximate distributions for distinct classes of data samples; computing a first partial Jensen-Shannon (JS) divergence and a second partial JS divergence based on the approximate distribution of the disparity affected class of data samples with reference to the approximate distribution of the control class of data samples; computing a disparity divergence based on the first partial JS divergence and the second partial JS divergence; generating a distribution-matching term based on the disparity divergence, wherein the distribution-matching term mitigates an inferential disparity between the control class of data samples and the disparity affected class of data samples during a training of an unconstrained artificial neural network; constructing a disparity-constrained loss function based on augmenting a target loss function with the distribution-matching term; and transforming the unconstrained ANN to a disparity-constrained ANN based on a training of the unconstraine

Abstract: A system and method includes generating approximate distributions for distinct classes of data samples; computing a first partial Jensen-Shannon (JS) divergence and a second partial JS divergence based on the approximate distribution of the disparity affected class of data samples with reference to the approximate distribution of the control class of data samples; computing a disparity divergence based on the first partial JS divergence and the second partial JS divergence; generating a distribution-matching term based on the disparity divergence, wherein the distribution-matching term mitigates an inferential disparity between the control class of data samples and the disparity affected class of data samples during a training of an unconstrained artificial neural network; constructing a disparity-constrained loss function based on augmenting a target loss function with the distribution-matching term; and transforming the unconstrained ANN to a disparity-constrained ANN based on a training of the unconstraine

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for machine learning model fairness and explainability. In some implementations, a method includes obtaining data relating to a plurality of potential borrowers; providing the data to the trained machine learning model; obtaining, by the trained machine learning model’s processing of the provided data, the one or more outputs of the trained machine learning model; and automatically generating a report that explains the one or more outputs of the trained machine learning model with respect to one or more fairness metrics and one or more accuracy metrics; and providing the automatically generated report for display on a user device.

Abstract: Systems and methods for training models to improve fairness.

Abstract: Systems and methods for training models to improve fairness.

Abstract: Systems and methods for training models to improve fairness.