Estimates

15min
/create_model
Create a baseline ROI estimation model that is siloed for your organization. These models are trained on a minimal amount of data.
request parameters
model_name: A reference name for the model. Must be unique among the models created in your account. Must not include spaces.
example request
JSON
{
  model_name: ["new_donors"]
}  
{
  model_name: ["new_donors"]
}  
﻿
response parameters
model_id: A unique ID associated with your model.
initial_evaluation_metrics: A nested JSON library of evaluation metrics associated with this starter model. As you fine-tune the model with your own data (using the /fine_tune_model endpoint), these metrics will improve.
example response
JSON
{
  model_id: ["sdf4dfC"],
  initial_evaluation_metrics: {
    donations: {
      area_under_roc_curve: 0.65,
      gain_detected_by_model: 0.23,
      mean_absolute_percentage_error: 0.34,
      precision: 0.74,
      recall: 0.84
    },
    amount_raised: {
      area_under_roc_curve: 0.61,
      gain_detected_by_model: 0.12,
      mean_absolute_percentage_error: 0.38,
      precision: 0.53,
      recall: 0.60
    },
    opt_outs: {
      area_under_roc_curve: 0.65,
      gain_detected_by_model: 0.10,
      mean_absolute_percentage_error: 0.12,
      precision: 0.82,
      recall: 0.79
    }
  }
}
{
  model_id: ["sdf4dfC"],
  initial_evaluation_metrics: {
    donations: {
      area_under_roc_curve: 0.65,
      gain_detected_by_model: 0.23,
      mean_absolute_percentage_error: 0.34,
      precision: 0.74,
      recall: 0.84
    },
    amount_raised: {
      area_under_roc_curve: 0.61,
      gain_detected_by_model: 0.12,
      mean_absolute_percentage_error: 0.38,
      precision: 0.53,
      recall: 0.60
    },
    opt_outs: {
      area_under_roc_curve: 0.65,
      gain_detected_by_model: 0.10,
      mean_absolute_percentage_error: 0.12,
      precision: 0.82,
      recall: 0.79
    }
  }
}
﻿
﻿
/fine_tune_model
Use your own internal data on dispatched text messages, the audiences that received them, and the aggregate observed outcomes to improve the model. The data you send to this endpoint will not be accessible in any way to users outside of your organization.
request parameters
model_id: Unique ID of the model you wish to fine-tune, as generated by the /create_model endpoint.
csv_url: Public URL of a CSV with the following fields: text_message, image (optional), audience_size, audience_percent_past_donors (optional), audience_mean_past_donation (optional), donations, amount_raised, opt_outs
authorize_payment: Boolean (true or false) indicating whether you are approving us to debit your credit balance.
example request
JSON
{
  object_type: ["matched_audience"],
  object_id: ["xcRfsdf3"],
  authorize_payment: [true]
}  
{
  object_type: ["matched_audience"],
  object_id: ["xcRfsdf3"],
  authorize_payment: [true]
}  
﻿
response parameters
status: A message indicating whether the payment was successful. Possible values include “success” and “error”.
error_details: If the payment was unsuccessful, details will be provided.
credits_used: The number of credits used in this transaction.
credits_remaining: The number of credits remaining in your account.
example response
JSON
{
  status: ["success"],
  error_details: [],
  credits_used: [450],
  credits_remaining: [49550]
}

{
  status: ["error"],
  error_details: ["Invalid ID provided."],
  credits_used: [0],
  credits_remaining: [50000]
}
{
  status: ["success"],
  error_details: [],
  credits_used: [450],
  credits_remaining: [49550]
}

{
  status: ["error"],
  error_details: ["Invalid ID provided."],
  credits_used: [0],
  credits_remaining: [50000]
}
﻿
﻿
/estimate_performance
Specify a model, high-level audience traits, and a text message. Then receive estimates of how that text message will perform with the given audience.
request parameters
model_id: Unique ID first generated by the /create_model endpoint.
audience_size: The number of people who will receive the text message.
audience_percent_past_donors: The percent of recipients who have made a known donation in the past. (optional)
audience_mean_past_donation: The average donation given by text message recipients in the past. (optional)
text_message: The text message you are intending to evaluate. The format should match the examples used in the /fine_tune_model endpoint.
image: The URL of any image you might be sending with your text message.
example request
JSON
{
  model_id: ["h535Dd9f"],
  audience_size: [55000],
  audience_percent_past_donors: [0.45],
  audience_mean_past_donation: [],
  text_message: ["Hi Dan! This is Tony the Tiger. I'm running in 
    a tight race against the Domino's Noid and I need $5 NOW!"
  image: ["https://test.com/avoidthenoid.png"]
}
{
  model_id: ["h535Dd9f"],
  audience_size: [55000],
  audience_percent_past_donors: [0.45],
  audience_mean_past_donation: [],
  text_message: ["Hi Dan! This is Tony the Tiger. I'm running in 
    a tight race against the Domino's Noid and I need $5 NOW!"
  image: ["https://test.com/avoidthenoid.png"]
}
﻿
response parameters
estimated_donations: The range of donations expected, with an 80% confidence level.
estimated_amount_raised: The range of total gross returns expected, with an 80% confidence level.
estimated_opt_outs: The range of opt-outs expected, with an 80% confidence level.
example response
JSON
{
  estimated_donations: {
    minimum: [15],
    maximum: [43],
    confidence_level: [0.8]
  },
  estimated_amount_raised: {
    minimum: [242],
    maximum: [629],
    confidence_level: [0.8]
  },
  estimated_opt_outs: {
    minimum: [3405],
    maximum: [12439],
    confidence_level: [0.8]
  }
}
{
  estimated_donations: {
    minimum: [15],
    maximum: [43],
    confidence_level: [0.8]
  },
  estimated_amount_raised: {
    minimum: [242],
    maximum: [629],
    confidence_level: [0.8]
  },
  estimated_opt_outs: {
    minimum: [3405],
    maximum: [12439],
    confidence_level: [0.8]
  }
}
﻿
﻿
﻿
Updated 24 Jan 2025
Audiences
Geographic filters
Estimates

/create_model

request parameters

example request

response parameters

example response

﻿

/fine_tune_model

request parameters

example request

response parameters

example response

﻿

/estimate_performance

request parameters

example request

response parameters

example response

﻿
