NVIDIA-Merlin / NVIDIA-Merlin/Merlin
[QST] Recommending items from transactions data
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 907
- Forks
- 129
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
I have a transactions data of user and items. Now I want to build a two tower model using this transaction data. Now my question is should I duplicate customer x item combinations based on number of transactions or just create one row per customer x item. If I just create one row how do I tell the mode to differentiate between a item that is purchased 5 times vs 1 time by the same customer
Thanks in advance
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
No files, tests, or entry points are mentioned. Start by clarifying whether this is a request for usage guidance or a library change, then define the expected handling of repeated customer-item transactions in a two-tower workflow. Done means the requested outcome and acceptance criteria are agreed.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100