# About the Richter's Predictor category
**URL:** https://community.drivendata.org/t/about-the-richters-predictor-category/4332
**Category:** Richter's Predictor
**Created:** [April 8, 2020, 3:57pm UTC](https://community.drivendata.org/t/about-the-richters-predictor-category/4332 "2020-04-08T15:57:36Z")
**Posts on this page:** 9
**Page:** 1
### Author:  [@bull](https://community.drivendata.org/u/bull)
#### Post date: [April 8, 2020, 3:57pm UTC](https://community.drivendata.org/t/about-the-richters-predictor-category/4332/1 "2020-04-08T15:57:36Z")
This category is for posts about the [Richter’s Predictor: Modeling Earthquake Damage](https://www.drivendata.org/competitions/57/nepal-earthquake/) competition. Please keep all posts here specific to the competition.
---
### Author:  [@Kritiker](https://community.drivendata.org/u/Kritiker)
#### Post date: [April 26, 2020, 8:50pm UTC](https://community.drivendata.org/t/about-the-richters-predictor-category/4332/2 "2020-04-26T20:50:04Z")
Just one question, why do you want to use F-score instead of ROC AUC to assess the models ?
---
### Author:  [@Bims](https://community.drivendata.org/u/Bims)
#### Post date: [May 4, 2020, 7:36pm UTC](https://community.drivendata.org/t/about-the-richters-predictor-category/4332/3 "2020-05-04T19:36:23Z")
I noticed the training labels data are much more than the training data. Any reason why, and what do I have to do.
---
### Author:  [@naveen\_9697](https://community.drivendata.org/u/naveen_9697)
#### Post date: [September 12, 2020, 2:29pm UTC](https://community.drivendata.org/t/about-the-richters-predictor-category/4332/4 "2020-09-12T14:29:50Z")
AUC can be used only when you have binary labels. But, we have 3 labels in this problem.
F1 score is basically a balance between Precision and Recall. It has multiple variants(micro, macro, weighted). Macro Averaged F1 Score is the evaluation metric here, which is nothing but, mean of the F1 scores of all classes. It is usually used to get unbiased estimate of multi-class classification problems and also to ensure under-sampled classes don’t have any impact on over-sampled classes in the final result.
---
### Author:  [@naveen\_9697](https://community.drivendata.org/u/naveen_9697)
#### Post date: [September 12, 2020, 2:30pm UTC](https://community.drivendata.org/t/about-the-richters-predictor-category/4332/5 "2020-09-12T14:30:33Z")
No, both of them are 260,601.
---
### Author:  [@luke\_stevens42](https://community.drivendata.org/u/luke_stevens42)
#### Post date: [November 5, 2020, 5:40pm UTC](https://community.drivendata.org/t/about-the-richters-predictor-category/4332/6 "2020-11-05T17:40:48Z")
How do we interpret the geo\_level features? I can’t find anything geographic in Nepal that would correspond to 30 regions for geo\_level\_1. Are they Districts/Wards/Municipalities? There are only 11 districts in the original dataset, so I’m guessing geo\_level\_1 has to be something else?
---
### Author:  [@apassan](https://community.drivendata.org/u/apassan)
#### Post date: [June 29, 2022, 3:18pm UTC](https://community.drivendata.org/t/about-the-richters-predictor-category/4332/7 "2022-06-29T15:18:26Z")
Did you ever figure out the categorical letter representations?
---
### Author:  [@Njdeep](https://community.drivendata.org/u/Njdeep)
#### Post date: [January 23, 2024, 1:47am UTC](https://community.drivendata.org/t/about-the-richters-predictor-category/4332/8 "2024-01-23T01:47:31Z")
I also encountered same
---
### Author:  [@Njdeep](https://community.drivendata.org/u/Njdeep)
#### Post date: [January 23, 2024, 1:49am UTC](https://community.drivendata.org/t/about-the-richters-predictor-category/4332/9 "2024-01-23T01:49:47Z")
No I also encountered same I also came across different data type of both the dataset