Predictive Account Scoring models
The Predictive Account Scoring model is a ready-to-use data science model that scores B2B accounts on their likelihood to convert based on their contacts' engagement patterns.
The Predictive Account Scoring model explained
The Predictive Account Scoring model generates numerical scores for accounts based on profile, revenue, and behavior data.
The account scores identify the propensity for accounts to make purchases.
Parameters of the model
When creating the model, you will need to define the following parameters for the model:
-
Algorithm: The algorithm is the piece of code that runs the model. When you select the Predictive Account Scoring B2B algorithm, you will need to define the additional lookback window parameter. Select the number of days as a lookback window: 90, 180, 270, or 360.
-
Queries: The queries selected for the model generate a dataset for model training and scoring.
-
Inputs: The inputs are query attributes from the Unity data model that are used for model training and scoring. You can't make changes to model inputs.
-
Outputs: The outputs are data objects and attributes from the Unity data model that are used to store the output values of the model. You can make updates to the default mapping of model outputs.
Model inputs
To generate values, the Predictive Account Scoring model uses the following data.
For the model to successfully run:
- Data needs to be ingested into all the input attributes below.
- Make sure the relationships between the respective account and contacts are established.
- The custom data object SalesData needs to be created with the following required attributes.
- OpportunityDate: Represents the date the opportunity was created (when the conversion occurred).
- Is_Converted: The value 1 represents conversion. The value 0 represents non-conversion.
- SourceAccountID: Account for which the conversion is captured.
Data object | Attribute | Data type | Description |
---|---|---|---|
Account | SourceID | String | The unique identifier for the source. |
Account | SourceAccountID | String |
The unique identifier for the account. |
Account | SICCode | String | The Standard Industrial Classification Code. |
Account | NAICSCode | String | The North American Industry Classification System Code. |
Account | AnnualRevenue | Float | The annual revenue of the company. |
Account | EmployeeTotal | Integer | The number of employees in the company. |
Account | LineOfBusiness | String | The industry of the contact. |
Account | YearEstablished | String | The year the company was established. |
Customer | SourceCustomerID | String | The unique identifier for the customer. |
Customer | String | The contact's email domain. | |
Customer | JobTitle | String | The job title of the contact. |
Customer | JobTitleLevel | String | The level assigned to each job title. |
Customer | okToCall | String | Flag identifying if the contact has given permission to be contacted by phone. |
Customer | okToEmail | String | Flag identifying if the contact has given permission to be contacted by email. |
Customer | okToNotify | String | Flag identifying if the contact has given permission to be contacted by push notification. |
Customer | okToText | String | Flag identifying if the contact has given permission to be contacted by text message. |
Customer | okToMail | String | Flag identifying if the contact has given permission to be contacted by mail. |
Event | SourceEventID | String | The unique identifier for the event. |
Event | Medium | String | The channel for the message, such Email, SMS, and Push. |
Event | Type | String | The type of event, such as View, Purchase, Buy, and Click. |
Event | EventTS | Timestamp | The date and time when the event occurred. |
MasterAccount | Country | String | The country of the contact. |
MasterAccount | State | String | The state of the contact. |
MasterAccount | City | String | The city of the contact. |
MasterAccount | ZipCode | String | The zip code where the contact resides. |
SalesData and Order | Is_Converted | Integer | Indicates when conversions occurred. The value 1 represents conversion. The value 0 represents non-conversion. |
SalesData and Order | OpportunityDate | Timestamp | The date when an opportunity was created (when the conversion occurred). |
SalesData | SourceAccountID | String | Unique identifier for the account. |
Model outputs
Output values will be stored in the Account_Score data object. You can review the lead score values for each contact in the Status attribute. Each status (cold, cool, warm, and hot) is based on a lead score generated from 0 to 100. Review the specific values and assessments below.
The following attributes will generate output values.
Attribute | Description | Data Type | Is Key attribute? |
---|---|---|---|
SourceAccount_ScoreID | The unique identifier for the data object. | String | Yes |
SourceID | The unique identifer for the source. | String | Yes |
SourceAccountID | The unique identifier for the account. | String | Yes |
ScoreTimestamp | The date and time when the lead score was generated. | String | No |
Score | The score generated for the contact. It is a numerical value from 0 to 100 | Integer | Yes |
Status | The status that assesses the contact based on the lead score | String | Yes |
The Status attribute will generate one of the following values based on the lead score.
Value | Assessment of account | Score |
---|---|---|
Cold | Not very active | 0-25 |
Cool | Slightly active | 26-50 |
Warm | Active | 51-75 |
Hot | Very active | 76-100 |
Create and use a Predictive Account Scoring model
To create and use a Predictive Account Scoring model, you will need to do the following:
-
Follow the steps for Creating Predictive Account Scoring models.
-
After creating the model, follow the steps for Running training and scoring jobs.
After the model runs and creates output values, you can do the following:
-
Access Account Scoring data to review the values in the output attributes.
-
Learn more about Using data science data for the specific needs of your organization.
-
If needed, you can review the data science model details.