The IBM Watson Analytics product documentation states that a prediction is a container for a predictive analysis and specifies the dataset that is being analyzed. A prediction can also specify the field properties that override the field properties in the dataset. By defining prediction-specific field properties, one can create custom analyses of the data.

Each Watson Analytics prediction you create can have different targets and inputs. After you create a prediction, you then review it to see the output from the analysis—and hopefully—new visual and text insights.

As a cue, the objective of this chapter's project is to determine what columns in our data affects the column position. In other words, we want to predict what combination of a player's characteristics or capabilities will best determine success for each position on a football team.

Although we have had a look at the raw data that we are using in this project, have we considered the quality of the data enough? Let's take a few moments to go back and look at our data's quality.