NVIDIA-Merlin / NVIDIA-Merlin/Transformers4Rec
Model is not generating accurate recommandations [QST]
Nobody has claimed this yet.
- 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
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- 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