Posted on

Big Data — It’s NOT for everyone.
But is it for you?

Initiating a big data project can be overwhelming. It’s not just one more thing on your plate — it’s more like three plates spinning at once. Take step one and see how you can use big data to solve a problem by locating hidden patterns in large volumes of data.

First, let’s figure out if big data will work for you — in three simple steps — without the mess of broken dishes.

Step 1 — Define the problem

Step 2 — Figure out how much data you need

Step 3 — Measure the problem against the data

Hint – If you don’t know your dilemma, what data you have, or where you want to end up then you need to focus on these three steps before diving into a data analysis project.

What’s your headache?

Do you have a headache? By a headache, I mean a pressing business need that needs to be addressed. Sam does.

Sam is a director of Admissions as a mid-size university, in charge of retaining students.

For many years the university has focused on the overall freshman year experience – and enjoyed a record number of freshman returning year two.

Recently, however, there has been a decline in the number of freshmen returning their sophomore year. Sam needs to know why, and how to reverse the decline. He’s hoping big data can help.

Is a big data project right for Sam?

Yes, he has a pressing business need — one that would apply to any business seeking to keep existing customers.

If his first-year retention was down by 13% last year, and if that trend continues for two more years, enrollment will be only 66% of its previous level — a critical business need!

Sam needs to know what’s causing this trend. What if the college’s rapid growth, or lack of new programming that caused students to look elsewhere after their freshman year? Which types of students left in droves, and which types remained?

Let’s see if data mining can identify the answers. Please read the next blog post to learn how.

 

 

Posted on

Where do you want to end up?

Now it’s time to measure the problem against the data to set the desired performance. Basically, how much do you need to change the situation, relative to the current benchmark to reach the desired level of improvement?

Sam, a director of Admissions at a mid-size university is in charge of retaining students. We have determined that he has:

  • A major problem that data analytics can help resolve
  • Enough data records to accomplish this task

His goal is to restore retention back to its previous level without increasing institutional costs. A retention rate increase of 2% to 2.5% would meet the goal.

In data mining terms, a moderate improvement is generally in the range of 10% to 100%. Sam’s need is in this range, at 25%. He needs a moderate performance increase.

Performance is the result of data mining effort, not a precursor to it. It helps us aim in the right direction, but we don’t know if the arrow will hit the bullseye until after we completed the analysis.

Basically, none of us have a crystal ball that shows the outcome in advance. That is why we are doing analysis, to look at the facts and uncover possible causes of the problem. The process will not necessarily confirm our assumptions.

That said, even without a guarantee, you can use our experience as a guide. IMA can assist with this if you are unsure how to measure or determine a moderate improvement. Incremental-to-moderate improvements are reasonable to expect with data mining. But don’t expect data mining to produce a miracle.

Please read the next blog post to learn how.

Posted on

What can we expect to learn from data analysis?

You’ve measured the value of the data by defining your business need. You are on your way to using customer data to help to improve your progress to your end goal. We find out by comparing likelihood to value.

Sam, a director of Admissions at a mid-size university, is in charge of retaining students. He is using data analysis to help understand a drop in retention.

When the analysis is applied to 1,000 student records, it will sort the data against the four factors Sam has selected. It will show which – if any – is causing enrollment to decline.

  • The student’s course of study
  • Net price
  • When they applied
  • High school GPA
                                  Figure A

It could be any of these, a combination of factors, or we might find no correlation. Unfortunately, — uncertainty is not a friend to data analytics. Fortunately, you can get help from IMA to assist you in taking these steps with certainty.

Each student is assigned a score on the likelihood they return. This was created by unlocking the unique patterns in data or data mining modeling.  The larger the score is, the more likely the outcome. Each dot or mark represents a student, and we can see that some are highly likely to return next year, while others much less so. This can be easily presented in the form of a graph as shown in Figure A.

Value is determined by defining your business need. For Sam, he defined his business need as improving retention without increasing costs. You can use your customer data or student data, in Sam’s case, to help to improve your mission without increasing capacity.

By comparing Likelihood against Value, Sam was able to build strategies and tactics to target the population, improving the rate by 2.5%.

Please read the next blog post to learn more.

 

Posted on

Tourist in a new town? Open up that map.

Think about data mining this way: you wouldn’t walk mindlessly around a large city and expect to end up seeing attractions you’d enjoy. You would plan it in advance and follow a map to get to your choices: museums, baseball park, or concert hall.

Without planning, you could stumble across an interesting restaurant, but you could be just as likely to spend the day bored, and tired, with aching feet.

Data mining can help reveal the direction you want to travel, but only if you have laid out the trip itinerary in advance.

In summary, to determine if data mining fits your organization, you must consider:

  • Your business need
  • Your available assets
  • The performance improvement required

If, like Sam, you answered yes to each of the questions posed you are well positioned to proceed with a data analysis project.

So how do you begin? Follow this same thought process before you spend a single dollar on a specific business need – whether it is the retention of students, attracting returning customers, raising funds, or expanding in a new market.

If you decide there is a fit, this preparation will serve you well in talking to your staff, stakeholders, leaders, and consultants who can help you move a data mining project forward.

You don’t have to do it alone

To get professional help with your data analysis needs, contact Ingram Market Analytics and request an Action Analytics Audit.

We will give you a tangible report, clear insights, an immediate course of action for a quick win, and increased ROI.

 

  • An Action Analytics Audit takes two sessions with your team
  • Results back to you in two weeks
  • We will explain, in detail, how to use the data we provide
  • You’ll have the power you need to make change happen.

ingrammaketanalytics.com
jingram@ingrammarketanalytics.com
412-478-3328