Event propensity model

Event propensity is a predictive model that determines the likelihood that a customer will perform a revenue-generating event within the next 30 days.

Use event propensity modeling to associate individual customers to specific events that, depending on the type of event, are most likely to lead to engagement with your brand. Customers are grouped by audience size and by ranking.

Use cases

The event propensity model enables support for marketing campaigns that benefit from knowing a customer’s likelihood to perform a revenue-generating event, including:

  1. Recommended audience sizes

  2. Ranking customers by propensity

Customer ranking

Use customer ranking to define an audience using the top N customers. Use customer ranking as an alternate to recommended audience sizes when an audience is too large (or small) or if a recommended audience size is unavailable for a specific event.

The Ranking attribute in the Event Propensity table ranks customer scores by event. A rank that is less than or equal to X will provide the top N customers with a propensity for this event. Combine this attribute with the Target Event attribute to build customer rankings for a specific revenue-generating event. You can access this attribute directly from the segment editor.

Build an event propensity model

You can build an event propensity model from the Customer 360 page. Each database that is a “customer 360” database and contains the Merged Customers, Unified Itemized Transactions, and Unified Transactions tables may be configured for predictive modeling. You may use other tables in that database that are unique by Amperity ID to extend predictive models.

Important

EPM is highly configurable, with the only table used by default being Merged Customers. The model requires that you select two other data assets with event-level data: one containing the target event, and one containing a revenue generating event.

The target event is the event we want to model, e.g. loyalty program signups, credit card signups, repeat bookings. The data asset should have one row per event, and must have a field for the event’s date or timestamp.

A revenue generating event is an event in which a customer spends money with your brand, e.g. a retail transaction or a booking. The data asset should also have one row per event, and must have fields for an event’s date or timestamp and revenue amount. You may also select other fields from the revenue generating event that you think would be helpful for modeling (e.g. purchase or booking channel).

Additionally, you may configure custom events as further inputs to the model. Custom event data assets are also expected to be one row per event.

For revenue generating events and custom events, there are configuration options for the event’s timestamp, and also the event’s realization date. For events, such as bookings, where a customer pays money at one point in time, but then “realizes” or consumes the good or service at another point in time, we strongly recommend supplying both fields to the model.

To build an event propensity model

Step 1.

Open the Customer 360 page, select a database, and then open the bottom (  ) menu and select Predictive models. This opens the Predictive models page.

Step 2.

Next to Event propensity, click Add model.

Assign a name to the event for which event propensity modeling will be built, and then click Continue. This opens the Predictive enablement page for predicted CLV models.

Step 3.

Configure the target event.

  1. From the Target event table dropdown, select the table in which the event for which event propensity modeling will be built.

  2. From the Target event date dropdown, select the field that contains the date on which the target event occurs.

  3. If this event is a repeating event enable the Repeat event checkbox.

Step 4.

Use the Customer exclusions field to use fields in the Customer Attributes table to identify customers who have purchase patterns that should be excluded from event propensity modeling.

For example, use cases for customer exclusions include:

  1. Ensuring that employees of your brand or resellers of products within your brand’s product catalog are excluded.

  2. Excluding customers who do not have a contactable email address or contactable physical address from direct mail campaigns.

Note

The list of fields in the Customer Attributes table that may be used for pCLV modeling are listed in the dropdown. Not all fields in the Customer Attributes table may be used with pCLV modeling.

Step 5.

Configure revenue events.

  1. From the Revenue event table dropdown, select the table in which revenue-generating events are located.

  2. From the Revenue event date dropdown, select the field that contains the date on which the revenue-generating event occurs.

  3. From the Revenue event realization date dropdown, select the field that differentiates between revenue generation and realization. For example, a hotel booking (generation) and a hotel stay (realization).

  4. From the Event revenue dropdown, select the field that captures the revenue from the realized event date.

Step 6.

Use the Additional event field to add more events to the event propensity model.

For each additional event, select an event table, and event date field, and additional features in that table that should be associated to the event.

Step 7.

Click Start validation.

Use in segments

The following table describes the fields that are available when using event propensity modeling in segments.

Column name

Data type

Description

Amperity ID

String

The unique identifier that is assigned to clusters of customer records that all represent the same individual. The Amperity ID does not replace primary and foreign keys, but exists alongside them within unified profiles.

Note

The Amperity ID is a universally unique identifier (UUID) that is represented by 36 characters spread across five groups separated by hyphens: 8-4-4-4-12.

For example:

123e4567-e89b-12d3-a456-426614174000

Audience Size Large

Boolean

A flag that indicates the recommended audience size. When this value is True the recommended audience size is large.

A large audience is predicted to include ~90% of future purchasers, while also including a high number of non-purchasers.

Audience Size Medium

Boolean

A flag that indicates the recommended audience size. When this value is True the recommended audience size is medium.

A medium audience is predicted to include ~70% of future purchasers, though it may also include a moderate number of non-purchasers.

Audience Size Small

Boolean

A flag that indicates the recommended audience size. When this value is True the recommended audience size is small.

A small audience is predicted to include ~50% of future purchasers, while including the fewest non-purchasers. Use a small audience size to help prevent wasted spend and reduce opt-outs.

Ranking

Integer

A ranking of customers by their score for this event. A rank that is less than or equal to X will provide the top N customers with an propensity for this event.

Score

Float

The strength of a customers’s propensity for this event, shown as an uncalibrated probability.

Tip

The score is used internally by Amperity, does not directly correlate to ranking and/or audience size, and should not be used in segments.

Sort results by Ranking, and then compare those results to audience sizes. Higher rankings within smaller audience sizes correlate with higher propensity.

Target Value

Integer

Revenue Event Days Since Last Event

Integer