--Ordinary least squares forecast for each customer for the next year.
select
cust_id,
max(year) +1 forecast_year,
-- y = mx+b
regr_slope(revenue, year)
* (max(year) + 1)
+ regr_intercept(revenue, year) forecasted_revenue
from customer_data
group by cust_id;
CUST_ID FORECAST_YEAR FORECASTED_REVENUE
------- ------------- ------------------
1 2018 730868
2 2018 50148
4 2018 7483
3 2018 -9920
下面是示例架构。或者,您可以使用此SQLFiddle。
create table customer_data
(
cust_id number,
year number,
revenue number
);
insert into customer_data
select 1, 2016, 679862 from dual union all
select 1, 2017, 705365 from dual union all
select 2, 2016, 51074 from dual union all
select 2, 2017, 50611 from dual union all
select 3, 2016, 190706 from dual union all
select 3, 2017, 90393 from dual union all
select 4, 2016, 31649 from dual union all
select 4, 2017, 19566 from dual;
该REGR
函数处理数字对,它不理解诸如“收入不能低于0”之类的业务规则。如果您希望将预测限制为始终保持在0或之上,则CASE
表达式可能会有所帮助:
--Forecasted revenue, with minimum forecast of 0.
select cust_id, forecast_year,
case when forecasted_revenue < 0 then 0 else forecasted_revenue end forecasted_revenue
from
(
--Ordinary least squares forecast for each customer for the next year.
select
cust_id,
max(year) +1 forecast_year,
-- y = mx+b
regr_slope(revenue, year)
* (max(year) + 1)
+ regr_intercept(revenue, year) forecasted_revenue
from customer_data
group by cust_id
);
CUST_ID FORECAST_YEAR FORECASTED_REVENUE
------- ------------- ------------------
1 2018 730868
2 2018 50148
4 2018 7483
3 2018 0