# Need suggestion

**URL:** <https://community.drivendata.org/t/need-suggestion/2055>\
**Category:** Pover-T Tests: Predicting Poverty\
**Created:** [February 24, 2018, 1:39am UTC](https://community.drivendata.org/t/need-suggestion/2055 "2018-02-24T01:39:35Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![maninesh](https://avatars.discourse-cdn.com/v4/letter/m/c0e974/32.png) [@maninesh](https://community.drivendata.org/u/maninesh)\
**Post date:** [February 24, 2018, 1:39am UTC](https://community.drivendata.org/t/need-suggestion/2055/1 "2018-02-24T01:39:35Z")

</div>

Hi All,

I am doing K fold split on training dataset and getting below result when calculating the log loss of individual country:  
A: ~ 0.30  
B: ~ 0.19  
C: ~ 0.02

But in final submission, the combined log loss is coming as high as 1.16. Can anyone please point out where I am possibly mistaken? Thank you in advance!

---

<div class="post-metadata">

**Author:** ![vijayabhaskar](https://avatars.discourse-cdn.com/v4/letter/v/df788c/32.png) [@vijayabhaskar](https://community.drivendata.org/u/vijayabhaskar)\
**Post date:** [February 24, 2018, 5:26am UTC](https://community.drivendata.org/t/need-suggestion/2055/2 "2018-02-24T05:26:31Z")

</div>

Are you submitting the predictions rather than probabilities?

---

<div class="post-metadata">

**Author:** ![maninesh](https://avatars.discourse-cdn.com/v4/letter/m/c0e974/32.png) [@maninesh](https://community.drivendata.org/u/maninesh)\
**Post date:** [February 24, 2018, 5:02pm UTC](https://community.drivendata.org/t/need-suggestion/2055/3 "2018-02-24T17:02:54Z")

</div>

@vijayabhaskar oh yes! indeed we are using probability correctly. yet somehow, log loss is coming very high.  
any suggestion to overcome this issue?