Mini-cases that connect the visual topics to working machine-learning workflows: dataset, pipeline, metric, common failure mode, and a notebook-ready starting point.
Real-data cases
Four cases, real datasets
Each case is intentionally small: enough structure to move from intuition to implementation, with a full JupyterLite notebook available when you want to run the workflow in the browser.
4 CasesReal DataMetricsNotebook Ready
Evidence note: Model-evaluation cases use established statistical methods. Market backtests are educational and heuristic until validated with point-in-time data, costs, slippage, and out-of-sample testing.
Notebook companion
Use the full notebook when you want the cases as executable Python workflows instead of copy snippets.