Category recommender v2
Replacing a FastText classifier with LLM classification
Context
The feature suggests a category when a seller lists a product — a follow-up to the v1 I had built earlier.
The FastText-based recommender had hit its ceiling on both accuracy and extensibility.
How I solved it
- More data and another training run would have fixed accuracy alone, but the deeper constraint was a taxonomy that keeps changing
- So I removed training from the loop entirely, replacing the FastText classifier with LLM-based classification
Result
- Classification accuracy went from 90% to 92%
- An average of 8,000 categories per marketplace now extend without retraining
- each new marketplace used to cost 70 minutes of it
FastText v170 min
LLM v2None