CART® Classification for Predict In-full Delivery

Use CART® Classification to use complex relationships with multiple predictors to predict in-full delivery.

This example applies to the Supply Chain Module. For more information, go to www.minitab.com/supply-chain-module.

Example

In-full delivery is the proportion of orders that are delivered completely in the first shipment. To calculate in-full delivery rate, divide the total number of in-full deliveries by the total number of deliveries.

In this worksheet, In Full is the response. The response event is In Full. Number of Items is the continuous predictor, and Type, Standard Parts, and Zone are categorical predictors.

C1-T	C2	C3-T	C4-T	C5-T
`In Full`	`Number of Items`	`Type`	`Standard Parts`	`Zone`
In Full	55	Porcelain	Yes	Priority
In Full	64	Ceramic	No	Priority
In Full	62	Ceramic	Yes	Central
Partial	61	Vinyl	No	Central

How-to

Choose Solutions Modules > Functions > Supply Chain KPIs, then select Launch.
Under Delivery, select In-full delivery.
Select Predict in-full delivery, then click OK.
Select CART® Classification, then click OK.
In Response, enter the binary variable that contains the delivery data. Binary variables are categorical variables that have two possible levels, such as pass/fail or true/false. The response is also called the Y variable.
In Response event, select the value that represents an in-full delivery.
In Continuous predictors, enter the continuous variables that may explain or predict whether a delivery is a partial delivery. The predictors are also called X variables.
In Categorical predictors, enter the categorical variables that may explain or predict whether a delivery is a partial delivery. The predictors are also called X variables.
Click OK.

Tip

For more information about this analysis, click Help in the main dialog box.