Skip to main content

​
Overview

These following tables are available within the Aampe data share:
  • AAMPE_USER_PROPENSITY_ESTIMATES - describes users in terms of Aampe labels
  • AAMPE_MESSAGE_DETAIL - describes Aampe message events, message and assignment details
While there are many potential applications, customers generally find these datasets useful for
  • Reporting and monitoring
  • Causal inference and offline message evaluation
  • Inputs into various machine-learning models

​
User Propensities

Aampe computes propensities based on your action sets (offering, value proposition, etc.).

The propensity for each label within a given action set reflects the agent’s estimate for how often that label will outperform the other label options. Said differently, if I were to simulate 100 messages from Aampe for each user, how often would the agent choose each label?

​
AAMPE_USER_PROPENSITY_ESTIMATES

ColumnTypeDescriptionExample Value
contact_idSTRUnique person identifier.asdf-1234
propensities_offeringARRAYUser propensities for each offering[{"label_id":5678, "propensity":0.5432, "label_name":"Food"},{"label_id":6789, "propensity":0.4568, "label_name":"Travel"}]
propensities_valuepropositionARRAYUser propensities for each value proposition[{"label_id":4567, "propensity":0.5432, "label_name":"Community"},{"label_id":5678, "propensity":0.4568, "label_name":"Affordability"}]
propensities_toneARRAYUser propensities for each tone label[{"label_id":3456, "propensity":0.5432, "label_name":"Funny"},{"label_id":4567, "propensity":0.4568, "label_name":"Serious"}]
propensities_timingARRAYUser propensities for each timing window[{"label_id":1234, "propensity":0.2, "label_name":"Mon-7am"},{"label_id":2345, "propensity":0.1, "label_name":"Mon-10am"}, ...]
propensities_channelARRAYUser propensities for each channel[{"label_id":2345, "propensity":0.75, "label_name":"push"},{"label_id":1234, "propensity":0.25, "label_name":"email"}]

​
User Profiles - Example Queries

// for a given user, what's their propensity for each offering label

SELECT 
  contact_id, 
  label_name, 
  propensity
FROM aampe_user_propensity_estimates,
UNNEST(propensities_offering)
WHERE contact_id = '1a2b3c4d'
ORDER BY propensity DESC

​
Aampe Messages

Agents save the details of each decision they make, including the parameters of the statistical models, sampling results, and the final decision result.

With a row for every message event this table helps with for day-to-day reporting and monitoring. It also plays a key role in offline analysis and causal inference.

​
AAMPE_MESSAGE_DETAIL

ColumnTypeDescriptionExample Value
aampe_message_id (pk)STRUnique identifier for a message eventxyz-123-abc
contact_idSTRUnique person identifier provided by customerasdf-1234
timestampTIMESTAMPTime of message delivery2025-08-18 12:50:02.499-04:00
timestamp_date (part)DATEDate of message delivery. Partition column.2025-08-18
timezoneSTRTimezone for message timestampAmerica/Chicago
formula_idINTID for a message group1234
formula_nameSTRName for a message groupComeback-50%Off
trigger_event_idSTRID for the trigger event associated with the message event0525c3b16a67
trigger_detailSTRUCT/ VARIANTKey/value pairs of Trigger details{"id":"62aa651a", "name":"Week1-3 NewUser"}
tagsARRAYTags associated with the message[{"id":"7c22372e", "name":"Services"},{"id":"ea8aac79","name":"Document"}]
timing_assignment_idSTRTiming assignment event IDd992-46d1
timing_assignment_detailARRAYKey/value pairs describing the timing assignment["label_set":"day_time", "label_id":1000000, "label_name":"Mon1-4am", "personalization_score":0.7738, "label_name":"Monday","assignment_type":"preferential"]
timing_assignment_dateDATEDate of timing assignment2025-08-17
channel_assignment_idSTRChannel assignment event ID46d1-864a
channelSTRMessage channel (push, email, sms, etc.)Email
channel_assignment_detailARRAYKey/value pairs describing the channel assignment["label_set":"channel", "label_id":123, "label_name":"Email", "personalization_score":0.7738, "assignment_type":"preferential"]
channel_assignment_dateDATEDate of channel assignment2025-08-17
copy_assignment_idSTRCopy assignment event ID17cebb7e-8ec0-4b40
copy_assignment_detailARRAYKey/value pairs describing the assignment of copy elements (labels)[{"label_set":"CallToAction", "label_id":"5410", "label_name":"SignUp", "score":0.918, "probability":0.8161, "aggregated_signal":25, "unique_action_id":6325}, {"label_set":"Greeting", "label_id":"5415", "label_name":"Hey", "score":0.775, "probability":0.789, "aggregated_signal":25, "unique_action_id":7148}]
copy_assignment_dateDATEDate of copy assignment2025-08-18
message_contentSTRUCT / VARIANTFull message body, title, etc.{"title":"We miss you!", "body":"<!DOCTYPE html>...n</body>\n</html>\n", "title_nchar":55, "body_nchar":11550}
recommender_detailsARRAYKey/value pairs describing recommender content when present[{"cms_item_id":1234, "recommendation_type":"AlgoV2", "brand_weight":13, "recommendation_score":.79}]

​
Aampe Messages - Example Queries

// for each message, what were the labels, label parameters, etc.?

SELECT 
    aampe_message_id,
    timestamp_date,
    label_set,
    label_name,
    score,
    probability,
    aggregated_signal
FROM 
    analytics_messages_detail,
    UNNEST(copy_assignment)
WHERE 
    aampe_message_id = '1234-asdf'