Today, businesses of all sizes use analytics. Take my favoritefruit vendor, for example. If you ask why he stopped selling in ourneighborhood market, he'll tell you it's because shoppers at thatparticular market are prone to negotiation, causing him to losemoney. At the market across town, on the other hand, he's foundgreat customers for whom he provides excellent service.

This is the heart of analytics. This fruit vendor testedservicing in my neighborhood and realized he was losing money. Howmany businesses today know who their most profitable customers are?Do they know who their most expensive customers are? Even if theyunderstand this data, have they built targeted efforts to acquiremore of the most profitable customers?

Credit unions, in particular, stand to gain tremendously fromcapturing data and using it for the segmentation of theirmembership.

Analytics is not pure science; it is part art as well. Creditunions that master the fine art of using analytical tools realizeincreased revenues and enjoy cost savings. But because scientificprinciples are often simpler to explain than artistic ones, let'slook at the four key steps of the scientific approach to dataanalytics.

1. Define the business problem

Analytics begins by identifying the right problem. It requiresunderstanding the facts, to which you have ready access, and thendrawing conclusions from them to identify the business problem thatneeds to be solved. For example, a credit union is suffering fromdeclining profits. By looking at the balance sheet, we realize thatrevenues have declined while the costs have remained constant.Through these two facts, we can identify a simple business problem– the credit union must reduce costs, or increase revenue, if itwants to have the same profitability as before.

2. Propose a hypothesis

Often called an “educated guess,” a hypothesis provides asuggested solution based on evidence. Researchers may test andreject several hypotheses before solving the problem. Taking thecredit union example above, there may be two sets ofhypothesis:

First, increase revenue by focusing on improved marketing orprice reductions to increase competitive stance. Second, reducecosts by cutting the operations budget or lowering marketingexpenses.

Interestingly, both hypotheses may lead to increasedprofitability by either increasing or decreasing the marketingbudget. Of course, there are several implications of each actionbeyond the primary implication, and all need to be evaluated. Thekey element of the hypothesis-building phase is that you shouldhave a mutually exclusive and collectively exhaustive set ofhypothesis. This requires considering all the possible sets ofrelevant hypotheses for the situation and ensuring they do notoverlap, and that together they are complete.

3. Test the hypothesis.

Let's continue with the example above and set up a test for thecredit union to learn whether increasing the marketing budget wouldaffect revenue. In this case, we would set up a test, running theexisting marketing programs and calling it “Group A.” In “Group B,”we would run the increased marketing program. At the end of theobservation timeframe (assume two to three months), we wouldmeasure revenue for each group to understand the differences.

4. Learn.

Let's assume that Group B performed better than Group A. Let'salso assume that at the same time we increased marketing, ourcompetitors decreased marketing. Now the question becomes, was theincremental benefit driven by our increased marketing, or was thebenefit due to the fact that competitors reduced their marketing?Assimilating all possible and relevant information is extremelyimportant in order to reach a good decision.

Scientists have been putting the above techniques to work for along time. Businesses, on the other hand, are just beginning to seethe value of scientific data analytics.

When you create an environment in which you are constantlytesting, you are constantly learning and evolving. With acommitment to the scientific process and a systematic approach totesting and learning, credit unions can evolve, as well, increasingknowledge and creating truly valuable and sustainable products.

RahulNawab is president of IQR Consulting in Santa Rosa,Calif.