Georgi Mullassery

A Python library for customer segmentation in marketing data pipelines — RFM analysis, clustering, segment profiling, and streaming updates in one import. ClusterAudienceKit is a Python library that replaces the scikit-learn + pandas + lifetimes stack for customer segmentation. If you've built this before, you've probably written hundreds of lines of boilerplate glue and still ended up with a pipeline that can't handle 100k customers in any reasonable time.

Python library for data quality and validation — declarative contract DSL, schema checks, drift detection, anomaly detection. 13× faster than pandera. PyPI: statguardian - Mullassery/Statguardian