Talk comments

Really good stuff!

A lot of concrete ideas that can be implemented starting from tomorrow (not now just because is Sunday :-P). Even if the example was symfony based (that should be mentioned in the abstract) the concept can be easily applied in every framework/context

Several interesting ideas and concepts, a lot of food for thoughts

I especially liked the first part, as some general concepts and classifications of recommendation engines were discussed. You did also pretty good in introducing some common problems such as sparsity / cold start.
As a suggestion: I found the example part with the tables a bit long: There were quite some slides about calculating the similarity between "item1 and item2" or "alice and bob". The prediction.io part covered the general server setup as well as the API - that was good to get an overview. Perhaps you could add a short section, where you discuss the benefits and shortcomings of prediction.io in comparision to e.g. graph databases or naive usage of SQL.

Good talk overall, found some interesting ideas and tools

Speaker has deep knowledge of the topic but he rushed through the presentation making some parts hard to follow. As someone already mentioned reorganizing the content and frame it in a story or use cases can help make the topic more accessible

Great talk, really inspiring!

Fun stuff, nice to see PHP used for this kind of thing. Thank you for showing, sharing and teaching.

Thank you, you made me think about the important stuff.