Understanding the business problem

As with any software project, the first thing is to agree on the business problem you are trying to solve. We have chosen a fictitious scenario for this book to keep it simple while focusing on the process. You can apply the same approach to more complex projects.

Let's assume that you work for an airline booking company as a lead data analyst. The business team of your company has reported that lots of customers complain about flights being delayed. It is causing the company to have bad customer experiences, and the phone staff spend lots of time explaining the details to customers. The business is looking at you to provide a solution to identify which airlines and which flights and times have a lower probability of delays so that the website can prioritize those airlines and, therefore, customers end up with fewer delays.

Let's take a breather here and analyze how we can solve this problem. Do we need ML here? If we take the historical...