PeoplePrism data comes from over 50 large commercially available consumer marketing data sets as well as publicly available data from the CDC and the US Census.

PeoplePrism helps resolve data gaps that are common in publicly available data sources, such as underreporting of unhoused populations, by compiling data from over 50 data sources and using predictive modeling methods to accurately cover data gaps.

PeoplePrism can gives the ability to look at multiple data variables at once, enabling users to segment broad populations by multiple variables to find unique sub-populations.

PeoplePrism leverages semi-supervised machine learning (ML) methods to train explainable predictive models. PeoplePrism generates modeling datasets that represent the US population with respect to legally protected groups, including age, race, and gender. PeoplePrism extend bias checks further to include representation across income groups and the urban-rural continuum. Additionally, each variable input into a model is examined for its distribution with respect to age, race, gender, income, and the urban-rural continuum to help ensure that they do not act as a proxy for any of those variables. This bias awareness and examination can also influence the strategy for model selection where only explainable and interpretable models are used to train and predict risk.

PeoplePrism is committed to maintaining the privacy of personal data, protecting user data and maintaining transparency with strict controls around data usage:

PeoplePrism data reflects predictive estimates based on multiple demographic and consumer marketing data sources. PeoplePrism updates underlying data and risk estimates on a regular basis (typically every one to two months, depending on the source). In other words, the data in this dashboard is updated on a consistently recurring basis as opposed to a real-time basis.

Populations that suffer disproportionately high rates of death and disease—such as racially and ethnically diverse populations, people with disabilities, and rural populations—are underrepresented in some health research, and their status as part of those groups is often not recorded in critical health care records. This lack of data is a serious barrier to advancing equity.

Race and ethnicity data are particularly essential to understanding and improving equity. However, race and ethnicity data on much of the US population is missing from many health-related data sets. Race and ethnicity are often poorly documented in commercial health records like insurance claims. Additionally, gaps in data and outdated information in public data sources like the US Census can hinder meaningful insights into race and ethnicity. These gaps can prevent recognition of very real health disparities and delay action to improve equity.

To enable meaningful action on equity, PeoplePrism uses predictive models based on the Bayesian Improved Surname Geocoding Method (BISG) to fill the gaps in missing race and ethnicity data (this method is used by government agencies like the Virginia Department of Health). In addition, PeoplePrism uses other data science methods to improve race and ethnicity predictive model accuracy. PeoplePrism includes self-reported race where such data is available and displays predicted race where no self-reported data is available.