# Implications of heavily correlated MMC and CORR?

**URL:** <https://forum.numer.ai/t/implications-of-heavily-correlated-mmc-and-corr/8072>\
**Category:** Data Science\
**Created:** [May 26, 2025, 4:59pm UTC](https://forum.numer.ai/t/implications-of-heavily-correlated-mmc-and-corr/8072 "2025-05-26T16:59:56Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![pharus](https://yyz1.discourse-cdn.com/flex009/user_avatar/forum.numer.ai/pharus/32/3301_2.png) [@pharus](https://forum.numer.ai/u/pharus)\
**Post date:** [May 26, 2025, 4:59pm UTC](https://forum.numer.ai/t/implications-of-heavily-correlated-mmc-and-corr/8072/1 "2025-05-26T16:59:56Z")

</div>

![image](https://canada1.discourse-cdn.com/flex009/uploads/numerai/original/2X/7/777fa14a57624bbaaf49f4c69fde47a3faabddab.png)

Does this imply the prediction is ‘unique’? Maybe even random/irrelevant?  
Is this model worth examining more?

Love to hear any thoughts about this.

---

<div class="post-metadata">

**Author:** ![wigglemuse](https://yyz1.discourse-cdn.com/flex009/user_avatar/forum.numer.ai/wigglemuse/32/3094_2.png) [@wigglemuse](https://forum.numer.ai/u/wigglemuse)\
**Post date:** [May 26, 2025, 5:18pm UTC](https://forum.numer.ai/t/implications-of-heavily-correlated-mmc-and-corr/8072/2 "2025-05-26T17:18:32Z")

</div>

Being correlated is not strange (generally going up & down at the same time), but having the same actual numerical values between the two is a bit more unusual as they are totally different things. That said, it isn’t especially interesting unless those scores are higher and it does it for a much longer time. I’ve had models track like that for months, and then diverge. What does it mean? Nothing special that I can see. If cumulative mmc is actually beating cumulative corr numerically over a long period (while still being good), that sounds like an interesting model. This one is too short of a time to say anything – just random probably.

---

<div class="post-metadata">

**Author:** ![pharus](https://yyz1.discourse-cdn.com/flex009/user_avatar/forum.numer.ai/pharus/32/3301_2.png) [@pharus](https://forum.numer.ai/u/pharus)\
**Post date:** [May 26, 2025, 6:01pm UTC](https://forum.numer.ai/t/implications-of-heavily-correlated-mmc-and-corr/8072/3 "2025-05-26T18:01:33Z")

</div>

Ah, thanks for your insights!

---

<div class="post-metadata">

**Author:** ![zentratech](https://avatars.discourse-cdn.com/v4/letter/z/f07891/32.png) [@zentratech](https://forum.numer.ai/u/zentratech)\
**Post date:** [June 5, 2025, 4:07pm UTC](https://forum.numer.ai/t/implications-of-heavily-correlated-mmc-and-corr/8072/4 "2025-06-05T16:07:54Z")

</div>

i agree wigglemuse! how did this go