NTILE() in BigQuery for non-uniform buckets - sql

Question

I'm trying to perform RFM segmentation on the Google Merchandise Store sample dataset on BigQuery. In my SQL query, NTILE(5) divides the rows into 5 buckets based on row ordering and returns the bucket number that is assigned to each row. In this case, each bucket are of equal size. Would like to find out how to create buckets of different sizes instead. For example, bucket 1 contains the bottom 10%, bucket 2 contains the next 20% of records etc. Thank you!
#standard SQL
SELECT
fullVisitorId,
NTILE(5) OVER (ORDER BY last_order_date) AS rfm_recency,
NTILE(5) OVER (ORDER BY count_order) AS rfm_frequency,
NTILE(5) OVER (ORDER BY avg_amount) AS rfm_monetary
FROM (
SELECT
fullVisitorId,
MAX(date) AS last_order_date,
COUNT(*) AS count_order,
AVG(totals.totalTransactionRevenue)/1000000 AS avg_amount
FROM
`bigquery-public-data.google_analytics_sample.ga_sessions_20170*`
WHERE
_table_suffix BETWEEN "101"
AND "801"
AND totals.totalTransactionRevenue IS NOT NULL
GROUP BY
fullVisitorId )

Answer 1

You can use row_number() and count(*) to define your own buckets:
SELECT fullVisitorId,
(CASE WHEN seqnum_r <= 0.1 * cnt THEN 1
WHEN seqnum_r <= 0.3 * cnt THEN 2
ELSE 3
END) as bin_r,
. . .
FROM (SELECT fullVisitorId,
MAX(date) AS last_order_date,
COUNT(*) AS count_order,
(AVG(totals.totalTransactionRevenue) / 1000000) AS avg_amount,
COUNT(*) OVER () as cnt,
ROW_NUMBER() OVER (ORDER BY MAX(date)) as seqnum_r,
ROW_NUMBER() OVER (ORDER BY COUNT(*)) as seqnum_f,
ROW_NUMBER() OVER (ORDER BY AVG(totals.totalTransactionRevenue)) as seqnum_m
FROM `bigquery-public-data.google_analytics_sample.ga_sessions_20170*`
WHERE _table_suffix BETWEEN "101" AND "801" AND
totals.totalTransactionRevenue IS NOT NULL
GROUP BY fullVisitorId
) rfm

Answer 2

Below is for BigQuery Standard SQL and assumes your initial query works for for you, SQL UDF NON_UNIFORM_BUCKET() does the trick for you
#standard SQL
CREATE TEMP FUNCTION NON_UNIFORM_BUCKET(i INT64) AS (
CASE
WHEN i = 1 THEN 1
WHEN i IN (2, 3) THEN 2
WHEN i IN (4, 5, 6) THEN 3
WHEN i = 7 THEN 4
ELSE 5
END
);
SELECT
fullVisitorId,
NON_UNIFORM_BUCKET(NTILE(10) OVER (ORDER BY last_order_date)) AS rfm_recency,
NON_UNIFORM_BUCKET(NTILE(10) OVER (ORDER BY count_order)) AS rfm_frequency,
NON_UNIFORM_BUCKET(NTILE(10) OVER (ORDER BY avg_amount)) AS rfm_monetary
FROM (
SELECT
fullVisitorId,
MAX(date) AS last_order_date,
COUNT(*) AS count_order,
AVG(totals.totalTransactionRevenue)/1000000 AS avg_amount
FROM
`bigquery-public-data.google_analytics_sample.ga_sessions_20170*`
WHERE
_table_suffix BETWEEN "101"
AND "801"
AND totals.totalTransactionRevenue IS NOT NULL
GROUP BY
fullVisitorId )