Ensemble predictor
AssigneeMicrosoft Technology Licensing, LLC
InventorsWeiwei Deng, Xiaoliang Ling, Feng Sun
Life of this patent
Estimating the term…
Abstract
Techniques for configuring and training an ensemble predictor for click probability of content on search engine results pages. In an aspect, a first stage machine learning algorithm, such as a neural network, is trained using a first training data set. The output of the trained first stage algorithm may be coupled to a second stage machine learning algorithm to form an ensemble predictor. In another aspect, the ensemble predictor is trained using a second training data set, using the output of the first stage algorithm to initialize a priori settings of the second stage algorithm.
Claims20
A method comprising:
- training a first machine learning model using a first training parameter set;
- subsequent to the training of the first machine learning model, training a second machine learning model using a second training parameter set, the training of the second machine learning model comprising initializing a setting of the second machine learning model using an output of the first machine learning model;
- and
- subsequent to the training of the second machine learning model, in response to receiving an input parameter set, generating an output variable comprising an estimate using the trained first machine learning model to generate the estimate and the trained second machine learning model to refine the generated estimate.
An apparatus comprising:
- a neural network configured to train a first machine learning model using a first training parameter set;
- a decision tree configured to train a second machine learning model using a second training parameter set, the training of the second machine learning model comprising initializing a setting of the second machine learning model using an output of the first machine learning model;
- and
- a an ensemble predictor configured to, subsequent to the training of the second machine learning model, in response to receiving an input parameter set, generate an output variable comprising an estimate using the trained first machine learning model to generate the estimate and the trained second machine learning model to refine the generated estimate.
An apparatus comprising a processor and a memory storing instructions for causing the processor to:
- train a first machine learning model using a first training parameter set;
- subsequent to the training of the first machine learning model, train a second machine learning model using a second training parameter set, the training of the second machine learning model comprising initializing a setting of the second machine learning model using an output of the first machine learning model;
- and
- subsequent to the training of the second machine learning model, in response to receiving an input parameter set, generate an output variable comprising an estimate using the trained first machine learning model to generate the estimate and the trained second machine learning model to refine the generated estimate.
Dependencies are inferred from the claim text.