-1

I run a download portal and basically what I want to do is after a user downloads a file i would like to recommend other related categories. I'm thinking of using google predict to do this but I'm not sure how to structure the training data. I'm thinking something like this:

category of the file downloaded (label), geo, gender, age

however that seems incomplete because the data doesn't have any information on the file downloaded. Would appreciate some advice, new to ML.

Patrick
  • 4,815
  • 11
  • 52
  • 55

1 Answers1

0

Here is a suggestion that might work...

For your training data, assuming you have the logs of downloads per user, create the following dataset:

download2 (serves as label), download1, features of users, features of download1

Then train a classifier to predict class given a download and user - the output classes and corresponding scores represent downloads to recommend.

Nikhil Kothari
  • 5,215
  • 2
  • 22
  • 28