Fundamental concept: Solving business problems with data science starts with analytical engineering: designing an analytical solution, based on the data, tools, and techniques available.
Exemplary technique: Expected value as a framework for data science solution design.
Ultimately, data science is about extracting information or knowledge from data, based on principled techniques. However, as we’ve discussed throughout the book, seldom does the world provide us with important business problems perfectly aligned with these techniques, or with data represented such that the techniques can be applied directly. Ironically, this fact often is better accepted by the business users (for whom it is often obvious) than by entry-level data scientists—because academic programs in statistics, machine learning, and data mining often present students with problems ready for the application of the tools that the programs teach.
Reality is much messier. Business problems rarely are classification problems or regression problems or clustering problems. They’re just business problems. Recall the mini-cycle in the first stages of the data mining process, where we focus on business understanding and data understanding. In these stages we must design or engineer a solution to the business problem. As with engineering more broadly, the data science team considers the needs of the business as well as the tools that might be brought ...