# Sprint 3 Results!

**URL:** <https://community.drivendata.org/t/sprint-3-results/6194>\
**Category:** Differential Privacy Temporal Map Challenge\
**Created:** [June 18, 2021, 8:17pm UTC](https://community.drivendata.org/t/sprint-3-results/6194 "2021-06-18T20:17:34Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![glipstein](https://yyz2.discourse-cdn.com/flex028/user_avatar/community.drivendata.org/glipstein/32/920_2.png) [@glipstein](https://community.drivendata.org/u/glipstein)\
**Post date:** [June 18, 2021, 8:17pm UTC](https://community.drivendata.org/t/sprint-3-results/6194/1 "2021-06-18T20:17:34Z")

</div>

**Results from the final algorithm sprint are in!** You can find a great summary of the sprint and an introduction to the winners and their approaches in the [results announcement](https://www.drivendata.co/blog/differential-privacy-winners-sprint3) blog post. You can also check out the Sprint 3 [leaderboard](https://www.drivendata.org/competitions/77/deid2-sprint-3-prescreened/leaderboard/) for final scoring results.

Top contestants of this final sprint demonstrated algorithms that produce records with both **more privacy _and_ greater accuracy** than the typical subsampling techniques used by many government agencies to release records. These results hold immediate promise for public safety communities and other groups interested in data sharing with the formal privacy guarantees offered by differential privacy.

Thanks for everyone’s hard work, and congratulations to all the participants in this sprint!

---

<div class="post-metadata">

**Author:** ![rmckenna](https://avatars.discourse-cdn.com/v4/letter/r/e36b37/32.png) [@rmckenna](https://community.drivendata.org/u/rmckenna)\
**Post date:** [June 24, 2021, 11:09pm UTC](https://community.drivendata.org/t/sprint-3-results/6194/2 "2021-06-24T23:09:27Z")

</div>

Thanks for all the work on organizing and running this competition, it was fun to be a part of it!

I’d love to take a closer look at the results than what is shown in the linked blog post — can you share how each team scored broken down by epsilon (1 and 10), metric (1, 2, and 3), and dataset (2016 and 2020)?

---

<div class="post-metadata">

**Author:** ![glipstein](https://yyz2.discourse-cdn.com/flex028/user_avatar/community.drivendata.org/glipstein/32/920_2.png) [@glipstein](https://community.drivendata.org/u/glipstein)\
**Post date:** [June 28, 2021, 5:57pm UTC](https://community.drivendata.org/t/sprint-3-results/6194/3 "2021-06-28T17:57:08Z")

</div>

Hi @rmckenna - Sure thing, here is a graph showing the final scoring performance by epsilon, dataset, and scoring component. Congrats again on the great work!

![image](https://canada1.discourse-cdn.com/flex028/uploads/drivendata1/original/2X/4/4e8edee8e3e775a3e78841051012a7ab77db36c3.png)