walk-forward-validation
Catch overfitting before you ship it: a walk-forward / held-out gate for any optimizer (Optuna, sweeps, prompt search). The highest score isn't deployable until it survives data it never saw. CLI + Python.
Temporal partitioning and backtesting utilities for time-correlated datasets.
Reproducible market research toolkit for weekly modeling, walk-forward evaluation, and baseline-plus-ML experiments.
