Cohort-based predictive data analysis
US11676727B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Aug 14, 2019 |
| Grant date | Jun 13, 2023 |
| Priority date | — |
| Expiry date | Jul 4, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG16H20/60
- WIPO fieldMedical technology
- WIPO sectorInstruments
Abstract
There is a need for more effective and efficient predictive data analysis solutions. This need can be addressed by, for example, obtaining prediction input objects each associated with a predictive entity; performing iterations of an iterative cohort generation routine until a qualified predictive model is identified, wherein each iteration comprises determining one or more predictive cohorts for predictive entities based on the prediction input objects, generating a predictive model based on the predictive cohorts, performing a predictive inference based on the predictive model to generate a current iteration prediction, generating a predictive score based on the current iteration prediction, and determining whether the predictive model is the qualified predictive model based on whether the predictive score exceeds a predictive score threshold; and performing cohort-based predictive data analysis based on the qualified predictive model to generate a respective final prediction for each predictive entity.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.