Mailman is a personalized email marketing automation system with user segmentation, NLP-driven email content generation and A/B testing analytics.
This project was developed as part of a freelance project that was published with the client's permission without real data. It's just a minimal PoC pipeline.
- User segmentation
Utilizes K-means, DBSCAN and ensemble approaches to group users based on purchase behavior, demographics and engagement level. - Email content generation
Integrates NLP techniques and LMs via HF transformers to generate personalized email subject lines and body content. - A/B testing & analytics
Implements statistical testing (t-test, ANOVA) and visualization to compare email variant performance, tracking open rates, click-through rates and conversions. - Email sending module
Supports automated email dispatching using SMTP with a simulation mode for testing.
-
Clone:
git clone git@github.com:avrtt/mailman.git cd mailman -
Create a virtual environment and install dependencies:
python3 -m venv venv source venv/bin/activate # Windows: venv\Scripts\activate pip install -r requirements.txt
-
Run the main script to execute the entire pipeline:
python src/main.py
Adjust parameters such as email server settings, model parameters and clustering options in src/config.py.
Apache 2.0.