Transaction Enrichment & Brand Classification

End-to-end machine learning pipeline for merchant brand and industry classification and banking transaction enrichment, with synthetic data generation, vectorization experiments, and an interactive Streamlit dashboard.

View the Project on GitHub d-daemon/transaction-enrichment-ml

Getting Started

Installation

uv venv
source .venv/bin/activate
uv pip install -r requirements.txt

Data Preparation

uv run python -m scripts.generate_synthetic_data_with_labels

Model Training

uv run python -m scripts.train_brand_classifier

Batch Categorization Enrichment Pipeline

uv run python categorize_transactions.py \
    --input data/synthetic_raw_transactions.csv \
    --output output/enriched_transactions.csv

Launch Dashboard

uv run streamlit run app.py

Open http://localhost:8501.

Home Architecture →