If a product is too complex, where is the complexity coming from? Which features are causing the explosion in the number of build combinations? The stairway to complexity tells us where to look.
The stairway to complexity shows how the number of unique configurations drops as features are removed. Here is another stairway for a backhoe with 30 features.
The number of build combinations drops from 934 down to 1 as we remove the features. Behind the graph is the actual list of features in the order they were removed. In the table below, the features are ranked from 1 to 30, corresponding to the steps in the graph.
If we want to simplify our product, this ranking of the features tells us where to start. The greatest contributor to complexity is the Buckets, of which there are 34 different kinds. The number of build combinations would drop from 934 to 838 if we didn’t have to worry about Buckets.
Is the ordering of the features in the stairway the same as the ordering by number of options? The first feature in the stairway is certainly the one with the most options (34). But Tran_Control has the second largest number of options (9), and doesn’t appear in the stairway until step 15. So there is more going on than just the number of options.
The amount of complexity introduced by a feature depends not just on the number of options, but on the relative popularity of the different options. Having two options that are split 50% to 50% is much worse than if they are split 90% to 10%. (See earlier post: Entropy of a coin toss.)
Introducing a new feature only increases product complexity if it splits existing configurations that would otherwise be the same. One manufacturer insisted that his product was so complex because it was produced for many different countries. But the number of unique build combinations was exactly the same whether the Country feature was included or not.
Comments Off