Adding Machine Learning and Data Science for personalizing User Experience

Hello everyone,

Is there any way to include data science and Machine Learning algorithms in the Rasa-backend in order to personalize the user experience according to their usage.

Hi @nike

That’s an interesting question! Could you please elaborate on that? What kind of personalization are you looking for?

Hi @degiz,

Thank you for your response.

I would like to elaborate my query with an example of an exercise recommendation bot.

Once the bot suggests an exercise, it can take input from the user regarding, if they were able to perform it or not and hence start recommending similar exercises. If they weren’t, then the next time, the bot should not recommend the same unless explicitly asked by the user.

I am not sure how to achieve this, but I feel Data Science and Machine Learning will play a key role in achieving the same.

Hope I was able to explain the personalization factor which I was looking for. Could you please let me know if this is possible?

Hey @nike

I see now, thanks! Looks like you want to build level 4 assistant :slight_smile:

Though we have some built-in features that you can use already, we’re not there yet completely.

  • Rasa will transfer all slots from previous session, so if there was something you’ve set before, you have access to that and can react. For “not recommending twice” you don’t event need the ML. Check the details here
  • Also, if that’s not enough, you have an access to the tracker store (meaning to all conversations), and you can in principle come-up with a ML “recommending” model for more complex use cases, but I don’t think it’s that easy

I hope that is helpful!

1 Like

Hi @degiz,

Thank you for your response. I got some better insights regarding my query.

1 Like