Predictive Query Language (PQL) Explained
00:00:00.000 | Kumo uses what they call the predictive query language or PQL.
00:00:04.700 | It's kind of like a SQL type syntax, which allows you to define your prediction parameters.
00:00:11.020 | So let's start with predicting the customer value over the next 30 days.
00:00:16.640 | So the way that we do that is like this.
00:00:19.500 | So we have our target, which you can see here.
00:00:22.820 | So the target is what follows predict here.
00:00:26.240 | So we have the predict statement, we're saying predict whatever is within our target here.
00:00:31.460 | Okay, we have the sum of the transactions price over the next 0 to 30 days into the future.
00:00:40.200 | And also we defined days here.
00:00:43.220 | So that is our target.
00:00:44.300 | But then we also have an entity, which is who or what are we making this prediction for?
00:00:50.640 | So here we're saying for each.
00:00:53.140 | So we're getting this sum of predictions broken down for each individual customer.