View Proposal

---

Proposer

Ian Tan

Title

Auto k-means with cluster labelling using LLM

Goal

An algorithm where the domain is specified and it will result in an appropriate number of meaningfully named clusters with the assistance of LLM.

Description

Auto k-means clustering is the automated process of determining the optimal number of clusters, k, in the k-means algorithm. This is typically an iterative process that attempts to find the ideal number of clusters. In this project, it will be influence by the domain that it is to be applied to and furthermore, this unsupervise machine learning method assigns a numeric identifier to the clusters where the project's second part is to assign meaningful names to the clusters based on the domain and the influential features that determined the clusters.

Resources

Subscription to LLM APIs.

Background

Students should have good algorithmic mindset, and the interest in using LLMs.

Url

Difficulty Level

High

Ethical Approval

None

Number Of Students

1

Supervisor

Ian Tan

Keywords

clustering, k-means, llm, unsupervised, machine learning

Degrees

Bachelor of Science in Computing Science