NVIDIA-Merlin / NVIDIA-Merlin/Transformers4Rec

Model is not generating accurate recommandations [QST]

Open
#770 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

status/needs-triage
Dominant language
Python
Stars
1.3k
Forks
165
Avg merge
1m
Merged PRs (30d)
2

Description

Hello. I've adapted t4rec model to my own e-commerce dataset and trained it but the model is not capturing the relationships between products and not giving a logical results. For the test i give him as input a transaction containing one product. The evaluation metrics also are very low(around 0.01). The loss function is decreasing but the predictions doesn't make sense. I tried many things like changing learning rate, batch size,... but doesn't work.

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

The report names no source file, test, or entry point. Start by reproducing the reported single-product evaluation on the author's e-commerce dataset and inspect the training configuration, input transaction format, and prediction metrics; done requires identifying a concrete cause and demonstrating logically related recommendations with improved evaluation results.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.