These are the formats our models expect the data to be in for ingestion. The standard and optional schemas are as follows:
| Data Source |
Data Description |
Optional/Required |
| Transactional Data |
A table where each row represents a transaction for a customer |
Required |
| Outbound Events |
A table where each row is an outbound event originating from the marketer. These data are usually messaging data (e.g., email, SMS) |
Optional |
| Inbound Events |
A table where each row is an inbound event collected by the marketer about a customer engagement. These data are usually website activity data |
Optional |
| Customer Attributes |
A table where each row represents a customer and each dimension is an attribute describing the customer. These could be loyalty status or demographics data. |
Optional |
Transaction Events
All transaction events with relevant discount and spend data. This table should be at the transaction level – one row per transaction. For transactions with multiple products purchased, pass product SKUs in an array in the product column.
| Metric |
Type |
Description |
Optional/Required |
| CUSTOMER_ID |
VARCHAR |
Customer identifier from client |
Required |
| SPEND |
FLOAT |
Total cost of the transaction |
Required |
| PRODUCT |
STRING |
Comma-separated list of item(s) purchased |
Required |
| TS |
INT |
Timestamp of conversion event |
Required |
| EVENT_ATTRIBUTE |
VARCHAR |
Other data describing the event (e.g., retail vs e-commerce, discount code) |
Optional |
| PRODUCT_ATTRIBUTE |
VARCHAR |
Other data describing the product (e.g., discontinued, seasonal, etc.) |
Optional |
Sample Schema:
| CUSTOMER_ID |
SPEND |
PRODUCT |
TS |
PURCHASE_TYPE (EVENT_ATTRIBUTE) |
PRODUCT_TYPE (PRODUCT_ATTRIBUTE) |
| C001 |
22.13 |
product1 |
1725478228 |
retail |
seasonal |
| C002 |
123.97 |
product1,product2,product3 |
1725478228 |
online |
promotional |
Outbound Events
This table should contain one engagement event per row, per customer. This data source is optional but will maximize the predictive power of the models if available.
| Metric |
Type |
Description |
Optional/Required |
| CUSTOMER_ID |
VARCHAR |
Customer identifier from client |
Required |
| TS |
INT |
Timestamp of outbound engagement event (e.g., sends) |
Required |
| CLICK_FLAG |
INT |
This is an event attribute which indicates a click engagement. This is the only required event attribute. |
Required |
| EVENT_ATTRIBUTE |
VARCHAR |
Other data describing the attributes (e.g., view, scroll, etc.) |
Optional |
| LABEL |
STRING |
Description of event (e.g., name of campaign) |
Optional |
| TYPE |
STRING |
Describe the type of event (e.g., email, SMS) |
Optional |
Sample Schema:
| CUSTOMER_ID |
TS |
LABEL |
TYPE |
CLICK_FLAG (EVENT_ATTRIBUTE) |
CAMPAIGN_TYPE (EVENT_ATTRIBUTE) |
| C001 |
1725478228 |
welcome_offer_campaign1 |
email |
1 |
welcome_campaign |
| C002 |
1725478228 |
winback_offer_campaign2 |
sms |
0 |
winback_campaign |
Inbound Events
Site, app, and all other engagement types. This data source is optional but will maximize the predictive power of the models if available.
| Metric |
Type |
Description |
Optional/Required |
| CUSTOMER_ID |
VARCHAR |
Customer identifier from client |
Required |
| TS |
INT |
Timestamp of inbound engagement event (e.g., pageviews, session) |
Required |
| LABEL |
STRING |
Description of event (e.g., page URL) |
Optional |
| TYPE |
STRING |
Describe the type of event (e.g., web session, page view, add to cart, scroll depth, Facebook, other) |
Optional |
| EVENT_ATTRIBUTE |
VARCHAR |
Other data describing the attributes (e.g., utm_source, utm_medium, utm_campaign) |
Optional |
Sample Schema:
| CUSTOMER_ID |
TS |
LABEL |
TYPE |
UTM_SOURCE (EVENT_ATTRIBUTE) |
UTM_CAMPAIGN (EVENT_ATTRIBUTE) |
UTM_MEDIUM (EVENT_ATTRIBUTE) |
| C001 |
1725478228 |
www.yourwebsite.com/blog |
pageview |
Facebook |
welcome_campaign |
Paid Social |
| C002 |
1725478228 |
www.yourwebsite.com/product1view |
pageview |
Google |
winback_campaign |
Display |
Customer Attributes
A table where each row represents a customer and each dimension is an attribute describing the customer. This table should contain only one row per customer.
| Metric |
Type |
Description |
Optional/Required |
| CUSTOMER_ID |
VARCHAR |
Customer identifier from client |
Optional |
| ATTRIBUTE |
VARCHAR |
Description of attribute (e.g., customer type, loyalty status, demographics, 3rd party data) |
Optional |
Sample Schema:
| CUSTOMER_ID |
CUSTOMER_TYPE |
GENDER |
| C001 |
premier |
female |
| C002 |
basic |
male |
