LLM-Based Flaky Test Prediction and Explainable Risk Analysis for CI/CD Pipelines

An LLM-based flaky test prediction and explainable risk analysis system for CI/CD pipelines.

An LLM-based flaky test prediction and explainable risk analysis system for CI/CD pipelines. It is offered as a reference project: a complete, worked example of how a system like this is designed, built and evaluated, so that a developer can study it, run it and learn from it.

It suits learners who want to run software the way production teams do: containers, automated pipelines, deployment, monitoring and rollback.

The main parts are explanations of each result (feature importance or visual evidence), containerised services, an automated build, test and deploy pipeline, monitoring and alerting, and safe rollback. The reference build uses LLM APIs, SHAP, Docker, Kubernetes, and GitHub Actions, with a clear project structure, setup instructions and sample data so that it can be run and extended.