Optimizing Data Processing and Feature Selection for Model Training
AssigneePaypal, Inc.
InventorsLichao Liu, Xuyao Hao, Zhanghao Hu
Life of this patent
Estimating the term…
Abstract
A method includes training a first machine learning model based on a set of training data and based on the training, determining a first performance metric corresponding to the first machine learning model. The method also includes determining one or more past performance metrics corresponding to one or more machine learning models that were previously trained based on the set of training data. Based on the first performance metric and the one or more past performance metrics, the method includes automatically selecting a second machine learning model to train based on the set of training data.
Claims20
A system, comprising:
- one or more hardware processors;
- and
- at least one memory storing computer-executable instructions, that in response to execution by the one or more hardware processors, causes the system to perform operations comprising:
- training a first machine learning model based on a set of training data, the first machine learning model being trained using a first data processing package from a set of data processing packages, a first feature selection package from a set of feature selection packages, and a first subset of model parameters from a set of model parameters;
- based on the training, determining a first performance metric corresponding to the first machine learning model;
- determining one or more past performance metrics corresponding to one or more machine learning models that were previously trained based on the set of training data;
- and
- based on the first performance metric and the one or more past performance metrics, automatically selecting a second machine learning model to train based on the set of training data, the automatically selecting further comprising:
- selecting a second data processing package from the set of data processing packages, a second feature selection package from the set of feature selection packages, and a second subset of model parameters from the set of model parameters.
A method, comprising:
- receiving, by a service provider system comprising one or more hardware processors, a set of training data;
- and
- iteratively selecting different machine learning models to train using the set of training data until a performance metric corresponding to a final machine learning model satisfies a metric threshold, wherein the iteratively selecting comprises selecting a first machine learning model of the different machine learning models based on respective performance metrics corresponding to previously trained machine learning models of the different machine learning models, and wherein the selecting the first machine learning model further comprises:
- selecting a first data processing package from a set of data processing packages, a first feature selection package from a set of feature selection packages, and a first subset of model parameters from a set of model parameters.
A non-transitory computer readable medium storing computer-executable instructions that in response to execution by one or more hardware processors, causes a system to perform operations comprising:
- receiving a set of training data;
- and
- iteratively selecting one or more machine learning models to train using the set of training data until a performance metric corresponding to a final machine learning model satisfies a metric threshold, wherein the iteratively selecting comprises selecting a first machine learning model of the one or more machine learning models based on respective performance metrics corresponding to previously trained machine learning models of the different machine learning models, and wherein the selecting the first machine learning model further comprises:
- selecting a first data processing package from a set of data processing packages, a first feature selection package from a set of feature selection packages, and a first subset of model parameters from a set of model parameters.
Dependencies are inferred from the claim text.