20240047070. MACHINE LEARNING TECHNIQUES FOR GENERATING COHORTS AND PREDICTIVE MODELING BASED THEREOF simplified abstract (Optum, Inc.)

From WikiPatents
Jump to navigation Jump to search

MACHINE LEARNING TECHNIQUES FOR GENERATING COHORTS AND PREDICTIVE MODELING BASED THEREOF

Organization Name

Optum, Inc.

Inventor(s)

Mark Gregory Megerian of Rochester MN (US)

Daniel George Mccreary of St. Louis Park MN (US)

MACHINE LEARNING TECHNIQUES FOR GENERATING COHORTS AND PREDICTIVE MODELING BASED THEREOF - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240047070 titled 'MACHINE LEARNING TECHNIQUES FOR GENERATING COHORTS AND PREDICTIVE MODELING BASED THEREOF

Simplified Explanation

The present disclosure describes a method for predicting risks by using data from different cohorts. This includes receiving data that defines the target data domain and the prediction feature. The method then determines inner cohort features based on a knowledge graph data object, which contains co-occurrence information of features from the dataset. Using a predictive machine learning model, the method generates risk scores for each entity in the outer cohort data subset, representing the likelihood of the entity being associated with features in the inner cohort data subset.

  • The method involves receiving data that defines the target data domain and the prediction feature.
  • Inner cohort features are determined based on a knowledge graph data object, which contains co-occurrence information of features from the dataset.
  • A predictive machine learning model is used to generate risk scores for each entity in the outer cohort data subset.
  • The risk scores represent the propensity of the entity being associated with features in the inner cohort data subset.

Potential applications of this technology:

  • Risk prediction in various domains such as healthcare, finance, and cybersecurity.
  • Identifying potential customers for targeted marketing campaigns.
  • Predicting the likelihood of fraudulent activities in financial transactions.

Problems solved by this technology:

  • Efficiently predicting risks by utilizing data from different cohorts.
  • Identifying entities in the outer cohort that are likely to be associated with features in the inner cohort.
  • Utilizing co-occurrence information from a knowledge graph data object to improve risk prediction accuracy.

Benefits of this technology:

  • Improved risk prediction accuracy by considering co-occurrence information from a knowledge graph data object.
  • Efficient identification of entities in the outer cohort that are likely to be associated with features in the inner cohort.
  • Potential cost savings by targeting resources towards entities with higher risk scores.


Original Abstract Submitted

the present disclosure provides methods, apparatus, systems, computing devices, and/or the like for performing risk prediction by receiving outer cohort definition data and inner cohort definition data, the outer cohort definition data representative of a target data domain with respect to a dataset, and the inner cohort definition data representative of a prediction feature with respect to the target data domain, determining one or more inner cohort features based at least in part on a knowledge graph data object using the inner cohort definition data, the knowledge graph data object including co-occurrence information of features from the dataset, and generating, using a predictive machine learning model, for each of one or more outer cohort entities associated with features in an outer cohort data subset, a risk score representative of a propensity of the outer cohort entity being an inner cohort entity associated with features in an inner cohort data subset.

Retrieved from "http://wikipatents.org/index.php?title=20240047070._MACHINE_LEARNING_TECHNIQUES_FOR_GENERATING_COHORTS_AND_PREDICTIVE_MODELING_BASED_THEREOF_simplified_abstract_(Optum,_Inc.)&oldid=32806"