# Conclusions and next steps from the Signals ML prospect scoring accelerator
> Complete the Snowplow Signals machine learning prospect scoring tutorial, and explore advanced real-time personalization use cases.
> Source: https://docs.snowplow.io/tutorials/signals-ml-prospect-scoring/conclusion/
> Documentation index: https://docs.snowplow.io/llms.txt

[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/snowplow-incubator/signals-notebooks/blob/main/web/web_prospect_scoring_end_to_end.ipynb)

In this accelerator you've learned how to build a prospect scoring system using Snowplow Signals together with a machine learning model, your own website, and your own Snowplow data.

What you achieved:

- Used Signals to calculate attributes
- Scored prospects using an ML model
- Served live prospect scores in the browser

This accelerator is a starting point for exploring and using Signals APIs for your own needs and use cases.

![Browser developer console showing live prospect scoring output: repeated prediction entries for a domain\_userid with scores around 0.009, alongside scoring attributes and explanations fetched from the Signals API](/assets/images/console_output-fea3b67475be2c3cdbc93d115d89dcb5.png)

## Next steps

Here are some ideas for further exploration:

- Define more Signals attributes that are specific for your use cases and tracking
- Act on the prospect scores and predictions in your application
- Use attributes to trigger actions and decisions without the ML step