something like this is done comparing monthly sums from a previous year with the current, to qualify the impact a campaign had in numbers. doing the difference you get the tendency for this year, and check if the actual result diverges from the tendency after the event.
The book is great. The problem with AI books and many technical books has to do with their huge size. The optimal instruction to learn AI for basic usage would be: provide an half page explanation and some working, tweakable examples.
This subject is difficult and requires a lot of time to understand and put something useful into practice. AI books appear frequently these days. I feel that most of books and tutorials fail to deliver good practical examples and meta-code, focusing more on mathematical proofs.