This project conducts customer credit risk assessment by preprocessing the data, applying various models, and evaluating their performance with and without SMOTE (Synthetic Minority Over-sampling Technique) to address class imbalance.
A smart data validation system for industrial sensors. It uses statistical Z-Score analysis to find "dirty" data and GPT-4o-mini to write technical quality reports. Designed to ensure AI reliability in Smart Factory environments.
An end-to-end AI pipeline for smart manufacturing. It uses a PyTorch Autoencoder to detect sensor anomalies and GPT-4o-mini to generate technical maintenance reports. Features SQLite database logging for full traceability and FastAPI for industrial integration.
Add a description, image, and links to the llm-reporting topic page so that developers can more easily learn about it.
To associate your repository with the llm-reporting topic, visit your repo's landing page and select "manage topics."