search

google-research / recsim

A Configurable Recommender Systems Simulation Platform
https://github.com/google-research/recsim
Apache License 2.0
732 stars 127 forks source link

Simulations with delayed feedback #24

Open sgaseretto opened 2 years ago

sgaseretto commented 2 years ago

Is there a way to simulate dalayed feedback with recsim? For example purchases that come a variable number of timesteps after the item was recommended?

cwhsu-google commented 2 years ago

Hi,

We can always log the most recent K recommended items inside the user state and the user remembers what to purchase later. Of course the size of user history has to be manageable. We can either limit K or use some sparse representation for the history if we know how many steps later the user may purchase the recommended item. Thanks for using RecSim.

On Thu, Jun 16, 2022 at 6:59 AM Sebastian Gonzalez Aseretto < @.***> wrote:

Is there a way to simulate dalayed feedback with recsim? For example purchases that come a variable number of timesteps after the item was recommended?

— Reply to this email directly, view it on GitHub https://github.com/google-research/recsim/issues/24, or unsubscribe https://github.com/notifications/unsubscribe-auth/ALVSYDWQRFO7VUU6OPAFRDLVPMXM5ANCNFSM5Y646X7A . You are receiving this because you are subscribed to this thread.Message ID: @.***>

sgaseretto commented 2 years ago

Thanks for the answer @cwhsu-google ! I'll try it