“When you’re cooking, preparation is an essential step. Ingredients need to be collected, peeled, marinated and put where you will be able to reach them when the oil is hot or the oven reaches the right temperature,” says Data Informed guest author, Bernard Marr, “this is also true in any business analytics and intelligence-driven process.”
With today’s data coming from an ever-increasing variety of sources, all of which store their valuable business insights in a variety of formats, the need to properly prepare your data before analysation has never been greater. But what, exactly, is data preparation?
In a nutshell, data preparation is the manipulation of data from unstandardised, unstructured or inconsistent data sources (scanned PDFs or manually inputted data for example) into a form suitable for further analysis and processing. It is a process that can account for up to 80% of your total time spent on a given project, but it is essential for ensuring a successful and informative end analysis.
Failing to properly prepare your data can not only make your results confusing, but potentially erroneous with inconsistent, poor quality insights from any future data mining or visualisation attempts likely. So what’s the best way to prepare your data, you might now ask?
Depending on the nature of your work, you might find yourself pulling from the same disparate data sources on a regular basis, or you might find yourself handling new data sources at regular intervals. If it’s the former, then you may well have developed personal checklists for prepping your data without even thinking about it, but if it’s the latter it can be difficult to come up with a thorough checklist for each step you need to take to ensure your data is sufficiently prepped. Generally, however, any operation that takes place on data before it is entered into your system and processed through a particular analytical system can be considered data preparation.
Frequently, data preparation includes these steps:
• Data Prep Strategy
• Data Cleansing
• Data Transformation
• Data Standardisation
• Data Augmentation
Do I Have to Do All This Preparation Myself?
The amount of data preparation required varies on a case-by-case basis. For example, if your data project involves only one type or source of data – just video, just the names and addresses of customers, or just transactional records – software like our very own IDEA Data Analysis can handle your data just fine in its raw state.
However, with most Big Data projects, the volume, variety and velocity of the data involved is too great for it to be practical to carry out these tasks manually. In these cases, thankfully, a large and growing self-service market for data preparation tools has emerged.
Because of the uniform nature of the operations and the repetitive tasks involved, data preparation is an ideal candidate process for automation, and one-stop-shop solutions often delivered through simple web interfaces that require a minimum of data science training are becoming increasingly common.
Just as with cooking, when it comes to business intelligence and data, good, solid preparation can often be the difference between success and failure. Regardless of which process from this list you decide is necessary in your situation, a consistent data prep strategy should be a priority for anyone involved in digital transformation and data-driven discovery.