# How document similarity works

**URL:** <https://discuss.elastic.co/t/how-document-similarity-works/95230>\
**Category:** Elasticsearch\
**Created:** [July 31, 2017, 6:49pm UTC](https://discuss.elastic.co/t/how-document-similarity-works/95230 "2017-07-31T18:49:30Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![ga48](https://avatars.discourse-cdn.com/v4/letter/g/e19adc/32.png) [@ga48](https://discuss.elastic.co/u/ga48)\
**Post date:** [July 31, 2017, 6:49pm UTC](https://discuss.elastic.co/t/how-document-similarity-works/95230/1 "2017-07-31T18:49:30Z")

</div>

Forgive me for the beginner question but can someone explain how basic document similarity works in Elastic search. Specifically, is something like KNN used to compute the similarity score between two document vectors or instead Naive Bayes, SVM or some other algorithm is used. Thanks

---

<div class="post-metadata">

**Author:** ![warkolm](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/warkolm/32/39224_2.png) [@warkolm](https://discuss.elastic.co/u/warkolm)\
**Post date:** [July 31, 2017, 11:36pm UTC](https://discuss.elastic.co/t/how-document-similarity-works/95230/2 "2017-07-31T23:36:11Z")

</div>

We use BM25, you can read more on this page [https://www.elastic.co/guide/en/elasticsearch/reference/5.5/index-modules-similarity.html](https://www.elastic.co/guide/en/elasticsearch/reference/5.5/index-modules-similarity.html)

---

<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:** [August 28, 2017, 11:36pm UTC](https://discuss.elastic.co/t/how-document-similarity-works/95230/3 "2017-08-28T23:36:46Z")

</div>

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