Microsoft Technology Licensing, LLC

Christopher Lee Weider

Ruth Kikin-Gil

Harsha Prasad Nori

A method and system for providing data imbalance detection and validation for a trained a ML model includes receiving a request to perform data imbalance detection on the trained ML model, identifying a feature of a dataset associated with the trained model for which data imbalance detection is to be performed, receiving access to the dataset, receiving access to the trained ML model, examining at least one of the dataset or outcome data generated by the trained ML model to determine a distribution of the feature or a distribution of the outcome data, and determining if the trained ML model exhibits data imbalance based at least in part on the distribution of the feature or the distribution of the outcome data.

Remote validation of machine-learning models for data imbalance

A method and system for performing semi or fully automatic data imbalance detection and correction in training a machine-learning (ML) model includes receiving a request to train the ML model, receiving access to a dataset for use in training the ML model, identifying a feature of the dataset for which data imbalance detection is to be performed, examining the dataset to determine a distribution of the feature across the dataset, determining if the distribution of the feature across the dataset indicates data imbalance, upon determining that the distribution of the feature across the dataset indicates data imbalance, identifying a desired distribution for the identified feature, selecting a subset of the dataset that corresponds with the selected feature and the desired distribution, and using the subset to train the ML model.

Method and system of performing data imbalance detection and correction in training a machine-learning model

A method and system for detecting imbalanced distribution of data that may signal bias in a dataset associated with training a machine-learning (ML) model includes receiving a request to perform data imbalance detection on the dataset associated with training the machine-learning (ML) model, identifying a feature of the dataset for which data imbalance detection is to be performed and examining the dataset to determine a distribution of the feature across the dataset. The result of the determination may then be presented in a user interface element to help identify data imbalance in the dataset.

Growing community of inventors

Redmond, WA, United States of America

Christopher Lee Weider