lyst / lyst/lightfm

Recommend for cold start user

Open
#718 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
5.1k
Forks
724
PR merge metrics
No merged PRs in 30d

Description

I trained a model using twitter data, my objective is recommend KOLs for projects in web3 community. When building model, i used followers, category and rawDescription of projects to build user_feature. Now, i want to predict for new project (not in interaction) with three above feature. Please help me!

Contributor guide

No contributing guide indexed for this repository

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

No file or test is named. First clarify whether this is a request for usage guidance or a missing cold-start capability, then inspect LightFM's hybrid-feature handling for unseen projects using followers, category, and rawDescription. Done should be defined as either documented usage or a reproducible implementation and test for predicting a new project.

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
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.