predict_momentum_LOAD: Test momentum prediction using LOAD strategy
In benSepanski/pfselect:

Test LOAD's strategy of predicting momentum. Returns each momentum prediction. See evaluate_momentum_at_window for a description of momentum

predict_momentum_LOAD(
  aggregated_momentum_data,
  regularization_factor,
  momentum_threshold,
  max_cv_window = NULL,
  momentum_colname = "momentum"
)

`aggregated_momentum_data`	A tibble of class `@eval{AGG_WINDOW_CLASS_NAME}` as returned from `aggregate_price_and_mean_windows`, with an added column of column name `momentum_colname` holding the momentum.
`regularization_factor`	A regularization factor used in the LOAD prediction, if a vector then cross-validates (at each step choosing the factor that had the least error over previous time, random first time)
`momentum_threshold`	The threshold to be classified as with momentum. If a vector then cross-validates. (at each step choosing the factor that had the least error over previous time, random first time)
`max_cv_window`	If `NULL` then checks over all past error, otherwise only checks the past `max_cv_window` time steps to determine error.
`momentum_colname`	The name of the column holding the true momentum values (as a string), defaults to `"momentum"`. Should be nonnegative momentum values (see `evaluate_momentum_at_window`)

aggregated_momentum_data with added columns: LOAD_prediction holding LOAD's predicted momentum for that time, regularization_factor holding the regularization factor used in that prediction, momentum_threshold holding the momentum threshold used in that prediction.

benSepanski/pfselect documentation built on May 1, 2020, 1:57 p.m.