Big Data & Analytics Solutions

Big Data Analytics – Test Before You Invest

Big data remains one of the hottest topics on the planet. Barely a week goes by where I don’t get some kind of offer related to big data—download a white paper, go to this conference, attend that webinar, look at this new product offering. It’s not just talk either–I’ve spoken with business leaders who are investing hundreds of thousands or millions of dollars on big data initiatives. Having always been a data guy, there’s clearly a lot of goodness in understanding and making sense of your data. But determining how to get value out of big data remains one of the top challenges and is, by far, where I spend the majority of my time.

The big data landscape continues to get more and more crowded. Big data solutions like Teradata, Cloudera and Netezza can certainly make it easier to store and process all of that data and analytics tools like SPSS, R and Tableau can help with analyzing it, but the question remains:

What business problem(s) are you trying to solve with your big data initiative?

As technology has gotten more powerful, there is a tendency to push the envelope and tackle big, hairy audacious challenges or maybe do big data for big data’s sake. Solving challenges is a good thing, like completing the NY Times crossword puzzle, but before you jump on the bandwagon and invest in a big data project, take a step back and do two things.

First, like Covey says, “begin with the end in mind.” Answer some very simple questions:

  • Is this a revenue generating or cost savings initiative?
  • Am I adequately staffed to support the effort for the long term?
  • What is my ideal “time to return” on this investment?

This will help you figure out the business case for this investment—or better yet, apply a specific business context to your big data initiative. So before writing a check, make sure you know the problem you’re trying to solve, double check that a big data project is the best way to solve it, and make sure the cost is worth the reward. As Tony Carter wrote, never solve a non-problem.

Once you’re sure you have built the business case and know the questions your big data initiative will answer, eat the elephant one bite at a time. Run a small pilot program on a sub-set of your data—with a specific business context and make sure that the big data analysis was the best way to solve “the” question you’re trying to answer. As you’re confident and successful with “phase one,” then go ahead and expand the investment. Otherwise, if you just jump into the deep end of the big data swimming pool without making sure you can swim, you and your career may be SOL—all thanks to big data.