Oracle SQL calculate average/opening/closing balances from discrete data - sql

Question

I have account balances like this
acc_no balance balance_date
account1 5000 2020-01-01
account1 6000 2020-01-05
account2 3000 2020-01-01
account1 3500 2020-01-08
account2 7500 2020-01-15
the effective balance for any day without a balance entry is equal to to the last balance. eg account1 balance on 2,3,4 Jan is 5000 etc.
I would like to produce the daily average, opening and closing balance from this data for any period. I came up with the following query and it works but it takes half an hour when I run it against the full data set. Is my approach correct or there is a more efficient method?
WITH cte_period
AS (
SELECT '2020-01-01' date_from
,'2020-01-31' date_to
FROM dual
)
,cte_calendar
AS (
SELECT rownum
,(
SELECT to_date(date_from, 'YYYY-MM-DD')
FROM cte_period
) + rownum - 1 AS balance_day
FROM dual connect BY rownum <= (
SELECT to_date(date_to, 'YYYY-MM-DD')
FROM cte_period
) - (
SELECT to_date(date_from, 'YYYY-MM-DD')
FROM cte_period
) + 1
)
,cte_balances
AS (
SELECT 'account1' acc_no
,5000 balance
,to_date('2020-01-01', 'YYYY-MM-DD') sys_date
FROM dual
UNION ALL
SELECT 'account1'
,6000
,to_date('2020-01-05', 'YYYY-MM-DD')
FROM dual
UNION ALL
SELECT 'account2'
,3000
,to_date('2020-01-01', 'YYYY-MM-DD')
FROM dual
UNION ALL
SELECT 'account1'
,3500
,to_date('2020-01-08', 'YYYY-MM-DD')
FROM dual
UNION ALL
SELECT 'account2'
,7500
,to_date('2020-01-15', 'YYYY-MM-DD')
FROM dual
)
,cte_accounts
AS (
SELECT DISTINCT acc_no
FROM cte_balances
)
SELECT t.acc_no
,(
SELECT eff_bal
FROM (
SELECT cal.balance_day
,acc_nos.acc_no
,(
SELECT balance
FROM cte_balances bal
WHERE bal.sys_date <= cal.balance_day
AND acc_nos.acc_no = bal.acc_no
ORDER BY bal.sys_date DESC FETCH first 1 row ONLY
) eff_bal
FROM cte_calendar cal
CROSS JOIN cte_accounts acc_nos
) t1
WHERE balance_day = (
SELECT to_date(date_from, 'YYYY-MM-DD')
FROM cte_period
)
AND t.acc_no = t1.acc_no
) opening_bal
,(
SELECT eff_bal
FROM (
SELECT cal.balance_day
,acc_nos.acc_no
,(
SELECT balance
FROM cte_balances bal
WHERE bal.sys_date <= cal.balance_day
AND acc_nos.acc_no = bal.acc_no
ORDER BY bal.sys_date DESC FETCH first 1 row ONLY
) eff_bal
FROM cte_calendar cal
CROSS JOIN cte_accounts acc_nos
) t1
WHERE balance_day = (
SELECT to_date(date_to, 'YYYY-MM-DD')
FROM cte_period
)
AND t.acc_no = t1.acc_no
) closing_bal
,round(avg(eff_bal), 2) avg_bal
FROM (
SELECT cal.balance_day
,acc_nos.acc_no
,(
SELECT balance
FROM cte_balances bal
WHERE bal.sys_date <= cal.balance_day
AND acc_nos.acc_no = bal.acc_no
ORDER BY bal.sys_date DESC FETCH first 1 row ONLY
) eff_bal
FROM cte_calendar cal
CROSS JOIN cte_accounts acc_nos
) t
GROUP BY acc_no
order by acc_no
The expected result
ACC_NO OPENING_BAL CLOSING_BAL AVG_BAL
account1 5000 3500 3935.48
account2 3000 7500 5467.74

Answer 1

Yes. You are unnecesary selecting from same table many times. Produce calendar as you did, join with your data partitioned by account and use analytic functions for computations:
select acc_no, round(avg(bal), 2) av_bal,
max(bal) keep (dense_rank first order by day) op_bal,
max(bal) keep (dense_rank last order by day) cl_bal
from (
select acc_no, day,
nvl(balance, lag(balance) ignore nulls over (partition by acc_no order by day)) bal
from (
select date_from + level - 1 as day
from (select date '2020-01-01' date_from, date '2020-01-31' date_to from dual)
connect by date_from + level - 1 <= date_to)
left join cte_balances partition by (acc_no) on day = sys_date)
group by acc_no
dbfiddle
Edit:
sometimes the first day of the month has no balance entry, it should
take form the last available
We have to treat first row in special way. It's done in subquery data, where in case of first row and null balance I run correlated subquery which looks for balance from max previous date.
with
cte_calendar as (
select level lvl, date_from + level - 1 as day
from (select date '2020-01-01' date_from, date '2020-01-31' date_to from dual)
connect by date_from + level - 1 <= date_to),
data as (
select lvl, day, acc_no,
case when balance is null and lvl = 1
then (select max(balance) keep (dense_rank last order by sys_date)
from cte_balances a
where a.acc_no = b.acc_no and a.sys_date <= day)
else balance
end bal
from cte_calendar
left join cte_balances b partition by (acc_no) on day = sys_date)
select acc_no,
max(bal) keep (dense_rank first order by day) op_bal,
max(bal) keep (dense_rank last order by day) cl_bal,
round(avg(bal), 2)
from (
select acc_no, day,
nvl(bal, lag(bal) ignore nulls over (partition by acc_no order by day)) bal
from data)
group by acc_no
dbfiddle
although I don't understand it yet
There are thre things, which are not obvoius here and you should know to understand query:
partitioned outer join. It's main part of the solution which produces whole period for each account. You can read about them here for instance,
lag() ignore nulls - fills null balance values, take them from previous not null,
max(bal) keep (dense_rank first order by day) takes balance value from first date for opening balance. last - from last row for closing balance.

Answer 2

If you can afford using first_value, last_value analytic functions, then this, based on my understanding of your description, may help:
with data as (
select 'account1' as acc, 5000 as balance, to_date('2020-01-01', 'YYYY-MM-DD') as d from dual
union all select 'account1' as acc, 6000 as balance, to_date('2020-01-05', 'YYYY-MM-DD') as d from dual
union all select 'account2' as acc, 3000 as balance, to_date('2020-01-01', 'YYYY-MM-DD') as d from dual
union all select 'account1' as acc, 3500 as balance, to_date('2020-01-08', 'YYYY-MM-DD') as d from dual
union all select 'account1' as acc, 7500 as balance, to_date('2020-01-15', 'YYYY-MM-DD') as d from dual
)
select acc, avg(balance) over (partition by acc order by balance) as average,
first_value(balance) over(partition by acc order by balance asc rows unbounded preceding) as first,
last_value(balance) over(partition by acc order by balance asc rows unbounded preceding) as last
from data
where d between to_date('2020-01-01', 'YYYY-MM-DD') and to_date('2020-01-06', 'YYYY-MM-DD')
order by acc
ACC | AVERAGE | FIRST | LAST
:------- | ------: | ----: | ---:
account1 | 5000 | 5000 | 5000
account1 | 5500 | 5000 | 6000
account2 | 3000 | 3000 | 3000
db<>fiddle here