Having now created several predictions (or predictive models) throughout the other chapters of this book, you no doubt have noticed that when you create a new prediction in Watson Analytics, the prediction opens automatically so you can view it. While you are viewing a prediction, you can see a summary of the most important insights in your data (that is, the Summary or Top Predictors page) and explore specific fields in detail (by just clicking on them).

Again, the spiral visualization—referred to by some as the predictive bullseye—on the Top Predictors page shows the top key drivers, or predictors, in color, with other found predictors in gray. The closer the predictor is to the center of the spiral or bullseye, the stronger that predictor is.

There is also a visualization for each key predictor, giving you information about what drives each behavior and outcome. If you click on one of the predictors (or hover over it), you see some details about it:

In our project's prediction, Watson Analytics has found that the Hobby/Interest column of data, is the top predictor of Dollar Amount Sold, but has a weak predictive strength (24.5%). More interesting though (as Watson directly points out) is that if we couple Hobby/Interest with Income Range, the two together have a much stronger predictive strength (41.5%).

The details of this relationship are visible if we click on the More details... link, and are shown here over two pages, the Main Insight page and the Details page:

The following screenshot shows you the Details page:

As with most features of Watson Analytics, rich visualizations along with detailed text explanations are generated and used to communicate key points and insights found in the data. For example, on the preceding Details page, we see this:

Dollar Amount Sold is a continuous target, so a linear regression (ANOVA) based approach is used.

Most of the textual insights and/or explanations contain hyperlinks so if you want to learn more about a term (such as linear regression), you can click on it:

Once again, the predict strength of the combination of Hobby/Interest with Income Range is just 41.5%. With a little effort, we can use Watson Analytics to improve on that percentage. That is, if we go back to the Top Predictors page and select Combination (under More Predictive), we can see that Education and Income Range together produce a predictive strength of 53.2 % (shown here):