01 / THE PRACTICAL QUESTION
A decision, before a model.
A quiet market becomes turbulent. A risk estimate based on a single long-run volatility can react too slowly to recent shocks.
Update tomorrow's risk using recent returns, then evaluate forecasts out of sample.
02 / DATA & COMPARISON
The idea in plain language.
GARCH lets recent shocks and previous volatility influence the next estimate. Volatility clustering means turbulent days tend to follow turbulent days.
- Conditional volatility
- An estimate of variability given the information currently available.
Data. Time-ordered returns and controlled volatility processes.
Baseline. Constant historical volatility on the same forecast horizon.
03 / THE EXPERIMENT
What the saved experiment shows.
The saved fit on 1,500 training observations produces a daily volatility forecast of 1.001%. This is a numerical forecast check; it does not establish superiority over constant volatility on future data.
Inspect the supporting resultEvidence record: research-validation.json#numerical_checks/04
Explore the related lab04 / RESULTS & LIMITATIONS
Evidence with its boundaries attached.
The related lab is a cross-project demonstration. Read this investigation’s evidence and limits before transferring its conclusions.
Inspect numerical checks and validation records
Loading validation evidence…
A good in-sample fit does not establish predictive accuracy under a new regime.
05 / REPRODUCE
Reproduce and challenge the result.
Code, configuration, and reproduction
The project contains its implementation, configuration, tests, and walkthrough. Download the lab configuration to record the exact parameters used in an interactive run.
Project code and walkthrough