# Forecasting with opensearch

**URL:** <https://forum.opensearch.org/t/forecasting-with-opensearch/9130>\
**Category:** Machine Learning\
**Tags:** discuss\
**Created:** [April 5, 2022, 5:02am UTC](https://forum.opensearch.org/t/forecasting-with-opensearch/9130 "2022-04-05T05:02:10Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![Oltre](https://avatars.discourse-cdn.com/v4/letter/o/54ee81/32.png) [@Oltre](https://forum.opensearch.org/u/Oltre)\
**Post date:** [April 5, 2022, 5:02am UTC](https://forum.opensearch.org/t/forecasting-with-opensearch/9130/1 "2022-04-05T05:02:10Z")

</div>

Hi,  
I have a warehouse system, and the products are consumed and reordered, can I use opensearch to monitor stocks and identify forecasting logic for reordering parts?

---

<div class="post-metadata">

**Author:** ![xyzheng](https://avatars.discourse-cdn.com/v4/letter/x/58f4c7/32.png) [@xyzheng](https://forum.opensearch.org/u/xyzheng)\
**Post date:** [April 6, 2022, 5:25pm UTC](https://forum.opensearch.org/t/forecasting-with-opensearch/9130/2 "2022-04-06T17:25:02Z")

</div>

hi Oltre, you can certainly use the Anomaly Detection function in OpenSearch to monitor your stocks, not forecasting though. We are actively working on bringing this into OpenSearch. Can you let us know a bit more details about your use case, just to help us to better design the feature? e.g. are you looking into realtime forecasting or like weekly trend analysis? do you want to see the forecasting result in a dashboard, or have it be part of the AD monitoring?

---

<div class="post-metadata">

**Author:** ![jdbright](https://sea1.discourse-cdn.com/flex019/user_avatar/forum.opensearch.org/jdbright/32/4979_2.png) [@jdbright](https://forum.opensearch.org/u/jdbright)\
**Post date:** [July 11, 2022, 8:01pm UTC](https://forum.opensearch.org/t/forecasting-with-opensearch/9130/3 "2022-07-11T20:01:26Z")

</div>

@Oltre Did you have specific use cases that you are solving more with more detail?

---

<div class="post-metadata">

**Author:** ![jdbright](https://sea1.discourse-cdn.com/flex019/user_avatar/forum.opensearch.org/jdbright/32/4979_2.png) [@jdbright](https://forum.opensearch.org/u/jdbright)\
**Post date:** [July 19, 2022, 3:57am UTC](https://forum.opensearch.org/t/forecasting-with-opensearch/9130/4 "2022-07-19T03:57:35Z")

</div>

For those who are tracking the Forecasting feature in the Forecasting with opensearch thread, I’ve opened up a [Github meta issue](https://github.com/opensearch-project/anomaly-detection/issues/615) to track the progress. We are eager to hear about use cases the community is interested in solving for.

---

<div class="post-metadata">

**Author:** ![amitgalitz](https://avatars.discourse-cdn.com/v4/letter/a/a3d4f5/32.png) [@amitgalitz](https://forum.opensearch.org/u/amitgalitz)\
**Post date:** [August 1, 2025, 10:04pm UTC](https://forum.opensearch.org/t/forecasting-with-opensearch/9130/5 "2025-08-01T22:04:49Z")

</div>

We have officially launched forecasting in OpenSearch in 3.1.0. Our documentation can all be found here: [Forecasting - OpenSearch Documentation](https://docs.opensearch.org/latest/observing-your-data/forecast/index/)

Feel free to add any issues or additional feature request in our github codebase: [GitHub - opensearch-project/anomaly-detection: Identify atypical data and receive automatic notifications](https://github.com/opensearch-project/anomaly-detection)