FindGovData.org

findgovdata.org is a website, created and operated by Amgix team, that allows you to search 540K+ publicly available U.S. government datasets using modern hybrid (exact keywords and related concepts) search algorithms. It enables you to find the data not only when you know the exact terminology used by the researchers, but by finding conceptually related information. Searching for childhood poverty stats may return no results in the traditional search, but finds Number of children in poverty dataset in this search, even though the record doesn't contain the word "stats" or "childhood".

We respect your privacy: we don't use cookies or trackers, we don't log your queries, no third-party services, and no generative AI/LLMs.

Motivation

United States government publishes large amounts of data via data.gov portal as a part of their transparency initiatives. Over 540 thousand datasets are there to explore for researchers, journalists and the public. However, if you struggle to find the data you need because the search is not finding relevant results, or you don't know the exact terminology used by government data publishers, the data is as good as non-existent.

We believe that Amgix technology can help with this by providing a better modern search experience as a public service, and as a demonstration of what our software can do with the real-world data.

Search Experience

How is the search experience at findgovdata.org different?

Better Result Relevance

By combining traditional search methodology with semantic (related concepts) search, enabled by a Machine Learning model, you are able to find the results that are more relevant to your query.

User Has Control

Our search works well by default. But if you want more control, you can adjust the parameters of your search in Advanced Options and by using multiple filtering tools.

It's Fast

Despite the large size of the datasets catalog (multiple gigabytes) the results appear as you type your query, in a blink of an eye.

It's Current

The data is periodically synced with the government catalog, so that you have the most up-to-date results.

Your Feedback is Welcome

Give it a try and let us know what you think by using the feedback button on findgovdata.org or our Contact page. We are always looking for ways to improve.

Technical Overview

If you are interested in technical details stay tuned for our deep-dive in the machinery powering the search.