Re:Categories of deep recommendation systems
by anjc on Saturday December 28, 2019 @04:09PM
(#21901739)
At some point you presumably have to assess user-similarity in order to let similar users recommend items to each other? How's this different from e.g. user-user CF in terms of compiling everyone's info into a single model? I'm not criticising but rather just curious
Re:Categories of deep recommendation systems
by fjabre on Saturday December 28, 2019 @07:54PM
(#21903029)
I haven't found enough of a need for it at this point to make the application more useful as it stands without making great effort in training the necessary models to assess user-similarity for example.
It is certainly faster to build an expert system that makes a lot of assumptions and iterate from there. There are plenty of use cases for ML and I hope to integrate it more into app some day to help automate repetitive tasks.
But there is no ML compiling a profile of every genre/title you've ever expressed interest in and then using that profile to guess what you want to see next like Netflix et al.