Projects / CPI Transformer Risk Dashboard / Demo
The dashboard is a Streamlit app. It shows the head-to-head RMSE scorecard, the forecast-vs-actual timeline on the held-out test set, and the top-5 SHAP macro drivers. Run it locally, or embed a hosted instance below.
The app reads pre-computed artifacts from artifacts/,
so it starts instantly after training.
# 1. Create the environment and install dependencies
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
# 2. Generate synthetic data (or drop your own macro_cpi.csv in data/raw/)
python -m src.utils.generate_synthetic
# 3. Train Transformer + ARIMA and write artifacts
python -m src.train_pipeline
# 4. Compute SHAP drivers
python -m src.explain_shap
# 5. Launch the dashboard
streamlit run dashboard/app.py