# How to improve precision of information retrieval

**URL:** <https://discuss.elastic.co/t/how-to-improve-precision-of-information-retrieval/143487>\
**Category:** Elasticsearch\
**Created:** [August 8, 2018, 10:16am UTC](https://discuss.elastic.co/t/how-to-improve-precision-of-information-retrieval/143487 "2018-08-08T10:16:53Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Nick\_Evans](https://avatars.discourse-cdn.com/v4/letter/n/e19adc/32.png) [@Nick\_Evans](https://discuss.elastic.co/u/Nick_Evans)\
**Post date:** [August 8, 2018, 10:16am UTC](https://discuss.elastic.co/t/how-to-improve-precision-of-information-retrieval/143487/1 "2018-08-08T10:16:53Z")

</div>

Maybe this question is too general but..  
I have a dataset of 30k+ documents which is loosely based on the gov2 dataset (I think it may be a subset).

I am struggling to improve the precision@10 metric, which is how this task will be evaluated.  
I have tried a custom analyzer that does some English possessive stemming and some other light stemming with kstem.

I have also combined a must with a match\_phrase query..

Any thoughts on how I can change my ES config to increase precision on this information retrieval task?

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\
**Post date:** [September 5, 2018, 10:16am UTC](https://discuss.elastic.co/t/how-to-improve-precision-of-information-retrieval/143487/2 "2018-09-05T10:16:55Z")

</div>

Closed on September 5, 2018, 10:16am UTC

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.