run_walk_forward: Walk-Forward Optimization Analysis
In PortfolioTesteR: Test Investment Strategies with English-Like Code

run_walk_forward

R Documentation

Walk-Forward Optimization Analysis

Description

Runs rolling IS/OOS optimization, reselects params each window, and backtests OOS performance (optionally with warmup tails).

Usage

run_walk_forward(
  prices,
  grid,
  builder,
  metric = NULL,
  is_periods = 52,
  oos_periods = 13,
  step = NULL,
  warmup_periods = 0,
  verbose = FALSE,
  light_mode = TRUE,
  precompute_all = TRUE,
  builder_args = list(),
  n_cores = 1
)

Arguments

`prices`	Data frame with Date column and symbol columns
`grid`	Data frame OR named list; each row/combination is a parameter set
`builder`	Function(prices, params, ...) -> weights data.frame (Date + assets)
`metric`	Function(backtest_result) -> scalar score (higher is better). Defaults to `metric_sharpe` if omitted/NULL.
`is_periods`	Integer, number of in-sample periods
`oos_periods`	Integer, number of out-of-sample periods
`step`	Integer, step size for rolling windows (default = oos_periods)
`warmup_periods`	Integer, warmup periods appended before each OOS
`verbose`	Logical, print progress
`light_mode`	Logical, passed to run_param_grid (kept for compatibility)
`precompute_all`	Logical, precompute indicators once and slice per window
`builder_args`	List, extra args passed to builder (e.g., indicator_cache)
`n_cores`	Integer (kept for API compatibility; ignored here)