The more orderly you are in your handling of data, the more consistent and better results you are like likely to achieve (with any project). The process for getting data ready for a machine learning algorithm (selecting, preprocessing, and transforming) can be accomplished using IBM Watson Studio with little programming or scripting required and, by leveraging the data refinery and catalog features, the work that you did at the start can be used over and over with little or no reworking required.
Here are a few parting words of advice:
- Take the time to add descriptions for your assets and always use descriptive names
- Manage your data assets well: remove extraneous copies or test versions right away and keep your catalogs clean
- Use the profiling feature religiously to better understand your assets
- Control who can access your assets by managing project and asset...