In Chapter 2, we elected to use a use case project that analyzed trip log data from a driving services company to determine which trip characteristics have a direct effect on a trip's profitability; what type of trip is most profitable, and which are prone to complications. This first, most basic project served to cover the fundamental components present in almost every Watson Analytics project—preparing the reader for the more complex projects presented in remaining chapters.

Key takeaways:

• The key capabilities of Watson Analytics include: automated data discovery, exploration, guided predictive analytics, recommended visualizations, dashboard creation, and visual storytelling.
• Projects start with gaining an understanding of the need or objective (for doing the project). After that, a review of the data fields available in the data is required.
• Projects may also include building a project data pool (or a single, secure location of all the data we intend to use) to be the input to our Watson project. The method used to create a data pool varies by project and requirement.
• To add data to Watson Analytics, go to the main or Welcome page, click on the + Add icon, then select: Drop file or browse or Upload data.
• Data quality assesses the degree to which a dataset is suitable for analysis. A shorthand representation of this assessment is the data quality score. The score is measured on a scale of 0-100, with 100 representing the highest possible data quality.
• To obtain a high data quality score, clean your data before you import it into Watson Analytics.
• You can use Refine to polish your data. This is sometimes referred to as tuning your data. When you refine a dataset in Watson, a new dataset is created that is related to your original dataset, but always saved as a separate version of the original dataset.
• Sometimes, especially if you are dealing with data completely new to you, you may spend time first exploring your data using Watson Analytics' Explore feature
• Using Watson Predict, Watson Analytics uses these sophisticated algorithms to quickly and efficiently deliver predictions based on your data.
• The predictions include visualizations and text descriptions of the analyses that Watson Analytics runs. You can use the visualizations to see the analyses at a glance and read the text for supporting explanations and statistical details.
• A Watson Analytics prediction is a container for a predictive analysis.
• When the prediction is ready, you can view the results starting with the Top Predictors page where you can select a predictor that is interesting and open its visualization.