Using LightFM for Retail Customer Recommendation based on purchased products
- Dominant language
- Python
- Stars
- 5.1k
- Forks
- 724
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
I am looking at using LightFM for recommending products to customers in retail stores based on the products the customer has bought in past. In the customer buying history, I have data regarding the products along with the purchase quantities for each product the customer has bought. The customer might have bought products with quantities ranging from 1 to 100 or more.
I am looking for suggestions on how I can convert these product-wise purchased quantities to the rating score of 1 to 5.
Looking for your suggestion.
Thank you.
Contributor guide
No contributing guide indexed for this repository
Research direction
No files, tests, or entry points are mentioned. Clarify whether this is seeking usage guidance or a repository change, and define how purchase quantities should map to interaction weights or ratings. Done would require an agreed mapping and a documented answer.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- machine-learning, python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100