# Dataset clarification

**URL:** https://forum.crunchdao.com/t/dataset-clarification/1190
**Category:** ADIA Lab
**Created:** [August 9, 2026, 1:20pm UTC](https://forum.crunchdao.com/t/dataset-clarification/1190 "2026-08-09T13:20:58Z")
**Posts on this page:** 2
**Page:** 1

<div class="post-metadata">

### Author: ![naval-harry](https://forum.crunchdao.com/user_avatar/forum.crunchdao.com/naval-harry/32/996_2.png) [@naval-harry](https://forum.crunchdao.com/u/naval-harry)
#### Post date: [August 9, 2026, 1:20pm UTC](https://forum.crunchdao.com/t/dataset-clarification/1190/1 "2026-08-09T13:20:58Z")

</div>

What is the intended purpose of these datasets?

X\_test.reduced.parquet  
y\_test.reduced.parquet  
y\_test\_index.reduced.parquet

And can we use them to train the model?

---

<div class="post-metadata">

### Author: ![enzo](https://forum.crunchdao.com/user_avatar/forum.crunchdao.com/enzo/32/15_2.png) [@enzo](https://forum.crunchdao.com/u/enzo)
#### Post date: [August 9, 2026, 2:15pm UTC](https://forum.crunchdao.com/t/dataset-clarification/1190/2 "2026-08-09T14:15:19Z")

</div>

Hello Harry,

- `X_test` is used to run the local test.
- `y_test` is used to score yourself locally.
- `y_test_index` is unused, but we left it to match the train files.

Of course, you can use them, but you will be overfit.  
And also, they will not be available in the cloud environment.