# ShatteredX's Improved & Compact Feature Set (225 features) for v4.3 Midnight Data

**URL:** <https://forum.numer.ai/t/shatteredxs-improved-compact-feature-set-225-features-for-v4-3-midnight-data/6982>\
**Category:** Data Science\
**Created:** [January 22, 2024, 8:25pm UTC](https://forum.numer.ai/t/shatteredxs-improved-compact-feature-set-225-features-for-v4-3-midnight-data/6982 "2024-01-22T20:25:36Z")\
**Posts on this page:** 1\
**Showing post:** 5

<div class="post-metadata">

**Author:** ![shatteredx](https://avatars.discourse-cdn.com/v4/letter/s/ee59a6/32.png) [@shatteredx](https://forum.numer.ai/u/shatteredx)\
**Post date:** [January 23, 2024, 4:00pm UTC](https://forum.numer.ai/t/shatteredxs-improved-compact-feature-set-225-features-for-v4-3-midnight-data/6982/5 "2024-01-23T16:00:09Z")

</div>

@halsmith99 Yeah I thought the same. I did use two different models, not the lightgbm one, to perform the brute-force feature evaluation.

@master_key That is really cool to see the proportion it shares with the other feature groups!

I also forgot to mention that my original inspiration for this experiment was @mdo 's BorutaShap thread where he created the small feature set. [Feature Selection with BorutaShap](http://forum.numer.ai/t/feature-selection-with-borutashap/4145) So I have been thinking about this idea for two years now apparently 😂 👴

---

_[View the full topic](https://forum.numer.ai/t/shatteredxs-improved-compact-feature-set-225-features-for-v4-3-midnight-data/6982)._