Robyn (version 3.11.1)

robyn_response: Response and Saturation Curves

Description

robyn_response() returns the response for a given spend level of a given paid_media_vars from a selected model result and selected model build (initial model, refresh model, etc.).

Usage

robyn_response(
  InputCollect = NULL,
  OutputCollect = NULL,
  json_file = NULL,
  robyn_object = NULL,
  select_build = NULL,
  select_model = NULL,
  metric_name = NULL,
  metric_value = NULL,
  date_range = NULL,
  dt_hyppar = NULL,
  dt_coef = NULL,
  quiet = FALSE,
  ...
)

Value

List. Response value and plot. Class: robyn_response.

Arguments

InputCollect

List. Contains all input parameters for the model. Required when robyn_object is not provided.

OutputCollect

List. Containing all model result. Required when robyn_object is not provided.

json_file

Character. JSON file to import previously exported inputs or recreate a model. To generate this file, use robyn_write(). If you didn't export your data in the json file as "raw_data", dt_input must be provided; dt_holidays input is optional.

robyn_object

Character or List. Path of the Robyn.RDS object that contains all previous modeling information or the imported list.

select_build

Integer. Default to the latest model build. select_build = 0 selects the initial model. select_build = 1 selects the first refresh model.

select_model

Character. A model SolID. When robyn_object is provided, select_model defaults to the already selected SolID. When robyn_object is not provided, select_model must be provided with InputCollect and OutputCollect, and must be one of OutputCollect$allSolutions.

metric_name

A character. Selected media variable for the response. Must be one value from paid_media_spends, paid_media_vars or organic_vars

metric_value

Numeric. Desired metric value to return a response for.

date_range

Character. Date(s) to apply adstocked transformations and pick mean spends per channel. Set one of: "all", "last", or "last_n" (where n is the last N dates available), date (i.e. "2022-03-27"), or date range (i.e. c("2022-01-01", "2022-12-31")). Default to "all".

dt_hyppar

A data.frame. When robyn_object is not provided, use dt_hyppar = OutputCollect$resultHypParam. It must be provided along select_model, dt_coef and InputCollect.

dt_coef

A data.frame. When robyn_object is not provided, use dt_coef = OutputCollect$xDecompAgg. It must be provided along select_model, dt_hyppar and InputCollect.

quiet

Boolean. Keep messages off?

...

Additional parameters passed to robyn_outputs().

Examples

if (FALSE) {
# Having InputCollect and OutputCollect objects
## Recreate original saturation curve
Response <- robyn_response(
  InputCollect = InputCollect,
  OutputCollect = OutputCollect,
  select_model = select_model,
  metric_name = "facebook_S"
)
Response$plot

## Or you can call a JSON file directly (a bit slower)
# Response <- robyn_response(
#   json_file = "your_json_path.json",
#   dt_input = dt_simulated_weekly,
#   dt_holidays = dt_prophet_holidays,
#   metric_name = "facebook_S"
# )

## Get the "next 100 dollar" marginal response on Spend1
Spend1 <- 20000
Response1 <- robyn_response(
  InputCollect = InputCollect,
  OutputCollect = OutputCollect,
  select_model = select_model,
  metric_name = "facebook_S",
  metric_value = Spend1, # total budget for date_range
  date_range = "last_1" # last two periods
)
Response1$plot

Spend2 <- Spend1 + 100
Response2 <- robyn_response(
  InputCollect = InputCollect,
  OutputCollect = OutputCollect,
  select_model = select_model,
  metric_name = "facebook_S",
  metric_value = Spend2,
  date_range = "last_1"
)
# ROAS for the 100$ from Spend1 level
(Response2$response_total - Response1$response_total) / (Spend2 - Spend1)

## Get response from for a given budget and date_range
Spend3 <- 100000
Response3 <- robyn_response(
  InputCollect = InputCollect,
  OutputCollect = OutputCollect,
  select_model = select_model,
  metric_name = "facebook_S",
  metric_value = Spend3, # total budget for date_range
  date_range = "last_5" # last 5 periods
)
Response3$plot

## Example of getting paid media exposure response curves
imps <- 10000000
response_imps <- robyn_response(
  InputCollect = InputCollect,
  OutputCollect = OutputCollect,
  select_model = select_model,
  metric_name = "facebook_I",
  metric_value = imps
)
response_imps$response_total / imps * 1000
response_imps$plot

## Example of getting organic media exposure response curves
sendings <- 30000
response_sending <- robyn_response(
  InputCollect = InputCollect,
  OutputCollect = OutputCollect,
  select_model = select_model,
  metric_name = "newsletter",
  metric_value = sendings
)
# response per 1000 sendings
response_sending$response_total / sendings * 1000
response_sending$plot
}