Back to results
US 11,699,105 B2Granted
Systems and methods for analyzing a list of items using machine learning models
AssigneeOracle International Corporation
InventorSudhakar Kalluri
Life of this patent
Estimating the term…
Abstract
Techniques are described for training machine learning (ML) models using one or more electronic lists of items previously used in campaigns and labeled with an engagement rate corresponding to the list. A vocabulary formed from a union of the one or more lists may then be used to generate at least some items of a target recipient list. An engagement rate for the target recipient list may be inferred for the target recipient list. Natural language processing (NLP) techniques may be also be applied to optimize an engagement rate of a target recipient list and/or select content for the list.
Claims20
One or more non-transitory computer-readable media storing instructions that, when executed by one or more hardware processors, cause performance of operations comprising:
- obtaining a training dataset comprising a plurality of recipient lists and, for each particular recipient list in the plurality of recipient lists, a respective value of a performance metric;
- generating a vocabulary comprising each recipient from the plurality of recipient lists;
- generating, for each particular recipient list, a respective feature vector that is (a) based at least in part on which recipients in the vocabulary occur in the particular recipient list and (b) associated with the respective value of the performance metric;
- training a machine learning model, based at least in part on the respective feature vector and the respective value of the performance metric for each particular recipient list;
- applying the machine learning model to a plurality of candidate recipient lists, to obtain a respective prediction of the performance metric for each candidate recipient list in the plurality of candidate recipient lists;
- selecting, based at least in part on the respective prediction of the performance metric for each candidate recipient list, a target recipient list from the plurality of candidate recipient lists.
3 more elements
A system comprising:
- at least one device comprising one or more hardware processors,
- the system being configured to perform operations comprising:
- obtaining a training dataset comprising a plurality of recipient lists and, for each particular recipient list in the plurality of recipient lists, a respective value of a performance metric;
- generating a vocabulary comprising each recipient from the plurality of recipient lists;
- generating, for each particular recipient list, a respective feature vector that is (a) based at least in part on which recipients in the vocabulary occur in the particular recipient list and (b) associated with the respective value of the performance metric;
- training a machine learning model, based at least in part on the respective feature vector and the respective value of the performance metric for each particular recipient list;
- applying the machine learning model to a plurality of candidate recipient lists, to obtain a respective prediction of the performance metric for each candidate recipient list in the plurality of candidate recipient lists;
- selecting, based at least in part on the respective prediction of the performance metric for each candidate recipient list, a target recipient list from the plurality of candidate recipient lists.
5 more elements
A method comprising:
- obtaining a training dataset comprising a plurality of recipient lists and, for each particular recipient list in the plurality of recipient lists, a respective value of a performance metric;
- generating a vocabulary comprising each recipient from the plurality of recipient lists;
- generating, for each particular recipient list, a respective feature vector that is (a) based at least in part on which recipients in the vocabulary occur in the particular recipient list and (b) associated with the respective value of the performance metric;
- training a machine learning model, based at least in part on the respective feature vector and the respective value of the performance metric for each particular recipient list;
- applying the machine learning model to a plurality of candidate recipient lists, to obtain a respective prediction of the performance metric for each candidate recipient list in the plurality of candidate recipient lists;
- selecting, based at least in part on the respective prediction of the performance metric for each candidate recipient list, a target recipient list from the plurality of candidate recipient lists;
- wherein the method is performed by at least device comprising one or more hardware processors.
4 more elements
Dependencies are inferred from the claim text.