After you export your Firebase data to BigQuery, you can query that data for specific audiences.
This article provides a number of templates that you can use as the basis for your queries. Remember to modify the example queries to address the specifics of your data; for example, change the table names and modify the date ranges.
These queries return the number of users in the audience. If you'd like to get the list of user IDs in the audience instead, then remove the outermost COUNT() function; for example, COUNT(DISTINCT user_id) --> DISTINCT user_id.
These queries use Standard SQL, so make sure you select that option before you run a query. (In BigQuery > SQL Workspace, click More > Query Settings. Under Additional Settings > SQL dialect, select Standard.)
Currently, this audience data is only informational, not actionable.
We'd love to hear whether you find these query examples useful, and if there are other types of audiences you'd like to query for. You can reply via a feature request with Firebase support.
In this article:
Purchasers
/**
* Computes the audience of purchasers.
*
* Purchasers = users who have logged either in_app_purchase or
* purchase.
*/
SELECT
COUNT(DISTINCT user_id) AS purchasers_count
FROM
-- PLEASE REPLACE WITH YOUR TABLE NAME.
`YOUR_TABLE.events_*`
WHERE
event_name IN ('in_app_purchase', 'purchase')
-- PLEASE REPLACE WITH YOUR DESIRED DATE RANGE
AND _TABLE_SUFFIX BETWEEN '20180501' AND '20240131';
N-day active users
/**
* Builds an audience of N-Day Active Users.
*
* N-day active users = users who have logged at least one event with event param
* engagement_time_msec > 0 in the last N days.
*/
SELECT
COUNT(DISTINCT user_id) AS n_day_active_users_count
FROM
-- PLEASE REPLACE WITH YOUR TABLE NAME.
`YOUR_TABLE.events_*` AS T
CROSS JOIN
T.event_params
WHERE
event_params.key = 'engagement_time_msec' AND event_params.value.int_value > 0
-- Pick events in the last N = 20 days.
AND event_timestamp >
UNIX_MICROS(TIMESTAMP_SUB(CURRENT_TIMESTAMP, INTERVAL 20 DAY))
-- PLEASE REPLACE WITH YOUR DESIRED DATE RANGE.
AND _TABLE_SUFFIX BETWEEN '20180521' AND '20240131';
N-day inactive users
/**
* Builds an audience of N-Day Inactive Users.
*
* N-Day inactive users = users in the last M days who have not logged one
* event with event param engagement_time_msec > 0 in the last N days
* where M > N.
*/
SELECT
COUNT(DISTINCT MDaysUsers.user_id) AS n_day_inactive_users_count
FROM
(
SELECT
user_id
FROM
/* PLEASE REPLACE WITH YOUR TABLE NAME */
`YOUR_TABLE.events_*` AS T
CROSS JOIN
T.event_params
WHERE
event_params.key = 'engagement_time_msec' AND event_params.value.int_value > 0
/* Has engaged in last M = 7 days */
AND event_timestamp >
UNIX_MICROS(TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 7 DAY))
/* PLEASE REPLACE WITH YOUR DESIRED DATE RANGE */
AND _TABLE_SUFFIX BETWEEN '20180521' AND '20240131'
) AS MDaysUsers
-- EXCEPT ALL is not yet implemented in BigQuery. Use LEFT JOIN in the interim.
LEFT JOIN
(
SELECT
user_id
FROM
/* PLEASE REPLACE WITH YOUR TABLE NAME */
`YOUR_TABLE.events_*`AS T
CROSS JOIN
T.event_params
WHERE
event_params.key = 'engagement_time_msec' AND event_params.value.int_value > 0
/* Has engaged in last N = 2 days */
AND event_timestamp >
UNIX_MICROS(TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 2 DAY))
/* PLEASE REPLACE WITH YOUR DESIRED DATE RANGE */
AND _TABLE_SUFFIX BETWEEN '20180521' AND '20240131'
) AS NDaysUsers
ON MDaysUsers.user_id = NDaysUsers.user_id
WHERE
NDaysUsers.user_id IS NULL;
Frequently active users
/**
* Builds an audience of Frequently Active Users.
*
* Frequently Active Users = users who have logged at least one
* event with event param engagement_time_msec > 0 on N of
* the last M days where M > N.
*/
SELECT
COUNT(DISTINCT user_id) AS frequent_active_users_count
FROM
(
SELECT
user_id,
COUNT(DISTINCT event_date)
FROM
-- PLEASE REPLACE WITH YOUR TABLE NAME.
`YOUR_TABLE.events_*` AS T
CROSS JOIN
T.event_params
WHERE
event_params.key = 'engagement_time_msec' AND event_params.value.int_value > 0
-- User engagement in the last M = 10 days.
AND event_timestamp >
UNIX_MICROS(TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 10 DAY))
-- PLEASE REPLACE YOUR DESIRED DATE RANGE. For optimal performance
-- the _TABLE_SUFFIX range should match the INTERVAL value above.
AND _TABLE_SUFFIX BETWEEN '20180521' AND '20240131'
GROUP BY 1
-- Having engaged in at least N = 4 days.
HAVING COUNT(event_date) >= 4
);
Highly active users
/**
* Builds an audience of Highly Active Users.
*
* Highly Active Users = users who have been active for more than N minutes
* in the last M days where M > N.
*/
SELECT
COUNT(DISTINCT user_id) AS high_active_users_count
FROM
(
SELECT
user_id,
event_params.key,
SUM(event_params.value.int_value)
FROM
-- PLEASE REPLACE WITH YOUR TABLE NAME.
`YOUR_TABLE.events_*` AS T
CROSS JOIN
T.event_params
WHERE
-- User engagement in the last M = 10 days.
event_timestamp >
UNIX_MICROS(TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 10 DAY))
AND event_params.key = 'engagement_time_msec'
-- PLEASE REPLACE YOUR DESIRED DATE RANGE.
AND _TABLE_SUFFIX BETWEEN '20180521' AND '20240131'
GROUP BY 1, 2
HAVING
-- Having engaged for more than N = 0.1 minutes.
SUM(event_params.value.int_value) > 0.1 * 60 * 1000000
);
Acquired users
/**
* Builds an audience of Acquired Users.
*
* Acquired Users = users who were acquired via some Source/Medium/Campaign.
*/
SELECT
COUNT(DISTINCT user_id) AS acquired_users_count
FROM
-- PLEASE REPLACE WITH YOUR TABLE NAME.
`YOUR_TABLE.events_*`
WHERE
traffic_source.source = 'google'
AND traffic_source.medium = 'cpc'
AND traffic_source.name = 'VTA-Test-Android'
-- PLEASE REPLACE YOUR DESIRED DATE RANGE.
AND _TABLE_SUFFIX BETWEEN '20180521' AND '20240131';
Cohorts with filters
/**
* Builds an audience composed of users acquired last week
* through Google campaigns, i.e., cohorts with filters.
*
* Cohort is defined as users acquired last week, i.e. between 7 - 14
* days ago. The cohort filter is for users acquired through a direct
* campaign.
*/
SELECT
COUNT(DISTINCT user_id) AS users_acquired_through_google_count
FROM
-- PLEASE REPLACE WITH YOUR TABLE NAME.
`YOUR_TABLE.events_*`
WHERE
event_name = 'first_open'
-- Cohort: opened app 1-2 weeks ago. One week of cohort, aka. weekly.
AND event_timestamp >
UNIX_MICROS(TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 14 DAY))
AND event_timestamp <
UNIX_MICROS(TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 7 DAY))
-- Cohort filter: users acquired through 'google' source.
AND traffic_source.source = 'google'
-- PLEASE REPLACE YOUR DESIRED DATE RANGE.
AND _TABLE_SUFFIX BETWEEN '20180501' AND '20240131';