RANDE NY: Race & Ethnicity Imputation (New York)

Impute race/ethnicity from names + NY addresses; returns privacy-aware tract/ZCTA summaries by default, per-row weights on request. Runs in your account.

View purchase options

Overview

Try agent mode

Create proposal

Ask question

RANDE NY estimates the most likely race/ethnicity of individuals from name and New York address using a published LSTM + geography model refined by 5-fold gradient-boosted soft-voting. Deploy it as a SageMaker real-time endpoint or Batch Transform in your own AWS account - your input records never leave your account and the vendor never sees your data. Default output is privacy-aware aggregate summaries by census tract and ZCTA (4 classes - White/Black/Hispanic/Asian - plus an explicit "unclassified" residual, with shares); per-row predictions with calibrated probability weights are available on request via a custom-attributes header. Method reproduces peer-reviewed accuracy that exceeds BISG/BIFSG with lower false-positive bias.

Highlights

Runs in the buyer's account (real-time endpoint or Batch Transform); inputs/PII never egress.
Aggregate-by-geography output by default (tract/ZCTA shares) to minimize per-record exposure; per-row weights via mode=rows.
Four reliable classes plus an explicit "unclassified" residual (Native/Other not reliably predictable); New York State scope; documented limitations.

Details

Sold by

aequumAI LLC

Introducing multi-product solutions

You can now purchase comprehensive solutions tailored to use cases and industries.

Learn more

Explore multi-product solutions

Features and programs

Financing for AWS Marketplace purchases

AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.

View financing details

Pricing

RANDE NY: Race & Ethnicity Imputation (New York)

Info

View purchase options

This product is available free of charge. Free subscriptions have no end date and may be canceled any time.

Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.

Vendor refund policy

This product is offered at no charge ($0). No fees are collected, so no refunds apply. For questions or support, contact terry@aequum.ai . If a paid version is offered in the future, refund terms will be stated at that time.

How can we make this page better?

Tell us how we can improve this page, or report an issue with this product.

Legal

Vendor terms and conditions

Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .

Content disclaimer

Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.

Usage information

Info

Delivery details

Amazon SageMaker model

An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.

Deploy the model on Amazon SageMaker AI using the following options:

Real-time inference

Deploy the model as an API endpoint for your applications. When you send data to the endpoint, SageMaker processes it and returns results by API response. The endpoint runs continuously until you delete it. You're billed for software and SageMaker infrastructure costs while the endpoint runs. AWS Marketplace models don't support Amazon SageMaker Asynchronous Inference. For more information, see Deploy models for real-time inference .

Batch transform

Deploy the model to process batches of data stored in Amazon Simple Storage Service (Amazon S3). SageMaker runs the job, processes your data, and returns results to Amazon S3. When complete, SageMaker stops the model. You're billed for software and SageMaker infrastructure costs only during the batch job. Duration depends on your model, instance type, and dataset size. AWS Marketplace models don't support Amazon SageMaker Asynchronous Inference. For more information, see Batch transform for inference with Amazon SageMaker AI .

Version release notes

Initial release. RANDE NY race/ethnicity imputation for New York State. Input: CSV of name + NY address (fname,mname,lname,housenumber,street,city,state,zip). Output: privacy-preserving aggregate race/ethnicity summaries by census tract and ZCTA (White/Black/Hispanic/Asian + unclassified residual) by default; per-row predictions with probability weights available via the custom-attributes header (mode=rows). Deploy as a real-time endpoint or Batch Transform; data stays in your account. Methodology exceeds BISG/BIFSG accuracy with lower false-positive bias.

Additional details

Inputs

Summary: CSV with a header row; one individual per row. Columns: fname,mname,lname,housenumber,street,city,state,zip. The name fields drive the name-based model; the New York street address (or at minimum city/ZIP) adds geographic signal. Any extra columns are passed through unchanged in per-row output. Scope: New York State (state = NY). Default response is aggregate tract/ZCTA summaries; set request header X-Amzn-SageMaker-Custom-Attributes: mode=rows for per-row predictions.

Input MIME type: text/csv

Real-time inference sample input data

fname,mname,lname,housenumber,street,city,state,zip James,A,Smith,100,Main St,Albany,NY,12207 Maria,,Garcia,55,Broadway,New York,NY,10006 Wei,,Chen,28,Mott St,New York,NY,10013 Aisha,M,Johnson,742,Grand Ave,Brooklyn,NY,11238 Robert,L,Williams,15,Elm St,Buffalo,NY,14201 Sofia,,Rodriguez,310,Park Ave,Rochester,NY,14607 David,,Kim,87,Queens Blvd,Queens,NY,11375 Emily,R,Brown,9,Lake St,Syracuse,NY,13202 Mohammed,,Ali,221,State St,Albany,NY,12210 Linda,J,Davis,46,Hudson Ave,Yonkers,NY,10701

Batch transform sample input data

Support

Vendor support

terry@aequum.ai

AWS infrastructure support

AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.

Get support

Similar products

Federal AI Compliance Plan — OMB M-25-21 / M-25-22 + CAIO Framework

By Kriv AI

Kriv AI builds Agency AI Compliance Plans under OMB M-25-21 (Apr 3, 2025) + M-25-22 (Apr 3, 2025). Scope: AI use-case inventory + OMB submission, high-impact determination (rights-impacting + safety-impacting + presumed-high-impact), CAIO reporting framework, annual AI strategy, minimum-practices packet, M-25-22 acquisition overlay (AI PWS clauses + data-rights + vendor DD + post-award + termination + subcontracting AI § (f)), FedRAMP Rev 5 + FISMA + NIST 800-53 Rev 5 AI Overlay + NIST AI RMF 1.0 GenAI Profile, DoD RAIEG + CDAO Toolkit (Enterprise), IC ICD 203 + ODNI AIM (Enterprise), SAM.gov Capability + past-performance narrative (Enterprise). Kriv SAM.gov active (UEI DATARJAUUXQ2, CAGE 1AEF1). Three tiers: $65K (4 wks, 1 bureau) / $145K (6 wks, agency/prime) / $275K (8 wks, cabinet / top-10 prime + DoD/IC + Capture).

View product

Customer reviews

Leave a review

Ratings and reviews

Info

0 ratings

5 star

4 star

3 star

2 star

1 star

0 reviews

No customer reviews yet

Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.