tensorflow / tensorflow/recommenders

[Question]: Using other metrics such as `AUC`.

Open
#486 15 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2k
Forks
300
PR merge metrics
No merged PRs in 30d

Description

In much of the literature / guides outside of this project AUC seems to be a popular metric for recommender systems. TF and Keras specifically has an implementation here.

However I am not sure on:

  • is this a valid metric to use for retrieval when using this project?
  • what hyperparams would be important to consider?
  • would the use of this as batch_metric make sense?

Thanks in advance!

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the TensorFlow/Keras AUC implementation linked in the issue and the project's retrieval metrics and batch_metric entry points. Determine whether AUC applies here, which hyperparameters matter, and what evidence or documentation would be needed to consider the question resolved.

Written by the indexing model from the issue text.

Assessment

Tech stack
keras, python, tensorflow
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.