Chapter 6. AI-Powered Diagnostic Analytics
Finding out what happened is only half as interesting as finding out why it happened. Although raw data can’t tell us the causal reasons why something happened, we can analyze the data for patterns and derive informed conclusions. At the very least, the patterns will point us in the right direction. In this chapter, you will learn how AI can help you reveal those interesting patterns in data automatically so you and your colleagues can concentrate on the interpretation and impacts of this data.
Use Case: Automated Insights
We’ll continue with the case study from the preceding chapter: in a fictitious manufacturing company, we support sales management in their decision-making process. In Chapter 5, we found that sales seemed to be slowly recovering after a period of sharp declines. Now we will go deeper and focus on understanding why certain trends have evolved.
Problem Statement
As the business analysts on the team, we want to help sales management find explanations for two of the observed revenue trends: why did sales numbers melt down so dramatically between 2006 and 2010, and what factors explain the slow recovery between 2010 and 2014? On a side note, if this were a real scenario, we probably would not be doing an analysis over an eight-year period because so many things would have changed. If it helps, imagine that we are a manufacturing company with a very long sales cycle.
This process would normally involve going through the ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access