robyn_modelselector: Robyn: Model Selection Viz

In laresbernardo/lares: Analytics & Machine Learning Sidekick

Robyn: Model Selection Viz

Description

Consider N models per cluster to select the right ones to study using several metrics to consider such as potential improvement on budget allocator, how many non-zero coefficients there are, R squared, historical performance, etc.

Usage

robyn_modelselector(
  InputCollect,
  OutputCollect,
  metrics = c("rsq_train", "performance", "potential_improvement", "non_zeroes",
    "incluster_models"),
  wt = c(2, 1, 1, 1, 0.1),
  top = 4,
  n_per_cluster = 5,
  allocator_limits = c(0.5, 2),
  quiet = FALSE,
  cache = TRUE,
  ...
)

## S3 method for class 'robyn_modelselector'
plot(x, ...)

Arguments

InputCollect, OutputCollect	Robyn output objects.
metrics	Character vector. Which metrics do you want to consider? Pick any combination from: "rsq_train" for trained R squared, "performance" for ROAS or (inverse) CPA, "potential_improvement" for default budget allocator improvement using allocator_limits, "non_zeroes" for non-zero beta coefficients, and "incluster_models" for amount of models per cluster.
wt	Vector. Weight for each of the normalized metrics selected, to calculate the score and rank models. Must have the same order and length of metrics parameter input.
top	Integer. How many ranked models to star? The better the model is, the more stars it will have marked.
n_per_cluster	Integer. How many models per cluster do you want to plot? Default: 5. Keep in mind they will all be considered for the calculations.
allocator_limits	Numeric vector, length 2. How flexible do you want to be with the budget allocator? By default, we'll consider a 0.5X and 2X range to let the budget shift across channels.
quiet	Boolean. Keep quiet? If not, message will be shown.
cache	Use cache functionality for allocator's results?
...	Additional parameters.
x	robyn_modelselector object

Value

list with data.frame and plot.

See Also

Other Robyn: robyn_hypsbuilder()

laresbernardo/lares documentation built on April 25, 2024, 5:31 a.m.