fuxictr-guide

What problem does it solve?

Provides clear guidance on using the FuxiCTR framework to configure and run CTR models such as DCN, DIN, DeepFM, and DCNv2.

Core Features & Use Cases

• Data preprocessing guidance: CSV → Parquet and feature_map.json generation
• Model selection and training workflows for common CTR models
• Use Case: Build and evaluate CTR models across standard datasets using run_expid.py

Quick Start

Train or evaluate a chosen FuxiCTR model using run_expid.py with a prepared configuration.