All projects

Category recommender v2

Replacing a FastText classifier with LLM classification

AbearApr 2024 – Jun 20243 mos

Context

The feature suggests a category when a seller lists a product — successor to the v1 I built as an intern.

Problem

The FastText-based recommender had hit its ceiling on both accuracy and extensibility.

How I solved it

  1. More data and another training run would have fixed accuracy alone, but the deeper constraint was a taxonomy that keeps changing
  2. So I removed training from the loop entirely, replacing the FastText classifier with LLM-based classification

Result

  • Adding a new category no longer requires retraining, so the taxonomy can grow freely

Impact

The taxonomy can change without anyone retraining a model.

Tech

PythonFastAPILangchainLLM
NextMultimodal emotion analysisF1 up 10%