---
title: "Comment by Sandro Volpicella on \"How we autodetect spam using Google's Vertex AI\" | Hashnode"
description: "This is really amazing! I think especially the fact of using an automated ML approach in combination with manual checkups (discord bot) is really useful. Great"
url: "https://hashnode.com/posts/how-we-autodetect-spam-using-googles-vertex-ai/61a8a2771e28ee7efba8c515/comment/61a8aac9be456923c52bd033"
---

[Discussion](https://hashnode.com/posts/how-we-autodetect-spam-using-googles-vertex-ai/61a8a2771e28ee7efba8c515)

Comment [How we autodetect spam using Google's Vertex AI](https://hashnode.com/posts/how-we-autodetect-spam-using-googles-vertex-ai/61a8a2771e28ee7efba8c515)

[Sandro Volpicella](https://hashnode.com/@SandroVolpicella)

[Dec 2, 2021](https://hashnode.com/posts/how-we-autodetect-spam-using-googles-vertex-ai/61a8a2771e28ee7efba8c515/comment/61a8aac9be456923c52bd033)

This is really amazing! I think especially the fact of using an automated ML approach in combination with manual checkups (discord bot) is really useful.

Great job 👍🏽

Are you still using only the displayName for predicting or the content as well?

[Sandeep Panda](https://hashnode.com/@sandeep)

[Dec 2, 2021](https://hashnode.com/posts/how-we-autodetect-spam-using-googles-vertex-ai/61a8a2771e28ee7efba8c515/comment/61a8aac9be456923c52bd033#reply-61a8acdebe456923c52bd067)

Thanks! As of now, we are simply considering `title`. This has reduced spam content by ~95%. I think we'll go deeper and check the content as well after observing the current setup for a while.
