DarkFoot101/Smart-Product-Pricing
Built a multimodal pricing system combining numerical, text, and image features with XGBRegressor, reducing SMAPE from 82% to 67%. Applied variance-based feature weighting to balance modalities and used a constrained LLM for quantity-aware calibration, correcting large pricing errors caused by bulk versus single-item ambiguity.
Stars
—
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Jan 20, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/DarkFoot101/Smart-Product-Pricing"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
truefoundry/models
Community-maintained registry of AI/LLM model configurations - pricing, features, and limits...
Mattbusel/LLMTokenStreamQuantEngine
A low-latency, C++-based simulation engine that ingests token streams from an LLM in real-time,...
VincenzoManto/llmtrim
A library for trimming tokens in encoding and decoding in LLM (Large Language Model)...