Have you ever been to a restaurant or cafe where they offer you a “bottomless” cup of coffee? This is the same concept as “free refills”, but I like the term bottomless because it’s more clever.

In either case, n-dimensional segmentation is like a bottomless cup of coffee. There is virtually no limit to how many ways you can segment your data and visitor activity. As a marketer and web analytics professional, I love n-dimensional analysis and segmentation – and in this blog post, I wanted to share with you why it’s so valuable and some ways you can profit from it.

What is “N-Dimensional”?
To make sure we’re all on the same page, let me start with a brief overview of the term “n-dimensional”. As I suggested above, n-dimensional refers to the concept of limitless dimensions. When coupled with analysis and segmentation, the basic idea is that you can drill into your data in limitless ways. While this may sound like an academic exercise, n-dimensional analysis and segmentation is incredibly powerful and can quickly deliver significant profit to your business.

Let’s start with an example
For instance, you might start with a keyword analysis for the term “web analytics”. Select your most relevant metrics, in this case Searches and Revenue, to understand the overall popularity and contribution of this keyword.

Now let’s say you want to drill deeper into this keyword to understand where it is most effective and least effective. Your first “dimension” may be products; in other words, you want to see which products are purchased by visitors from this keyword. You see “Apple iPod” tops the list, so you filter on this product to understand these customers better.

You may now wonder if these are new or repeat customers, so you pull up the “Customer Loyalty” report and notice that most purchasers are New. So you add “New” customers to your filter as well.

Now you’re curious if these New Customers are younger or older shoppers. So you bring up your Age Group report, and notice that most shoppers are from 18-24. You add this to your filter criteria as well.

At this point, you’d like to understand where all these people are visiting from. So you pull up the “Geography” report and see that most visitors originate from California and New York.

You’d like to try an email marketing campaign to these folks, so you pull up another Products report and analyze which products these visitors looked at but did not purchase. You see that many of these customers also viewed the iPod extended life battery in the same visit, but didn’t buy it. So now you extract the customer IDs for these, export them to your email marketing platform, and send out your remarketing campaign.

Now let’s take a step back and understand what you’ve just done. You’ve effectively segmented your entire website audience by 6 dimensions (keyword, purchased product, customer loyalty, age group, geography, and viewed product). This resulted in a highly targeted customer segment that you can now remarket to based on their actual behavior and product affinities. How cool is that?

N-dimension = Bottomless segmentation
So the critical message is that n-dimensional analysis and segmentation allows you to slice and dice any data point by any other data point. As you do this, you’re drilling deeper and deeper into your data and creating highly targeted segments of your overall traffic. I often call this “progressive filtering”, because your filter criteria effectively narrow the scope of your segment with each incremental step. N-dimensional analysis is also sometimes referred to as dynamic filtering, drilling down, and for the adventurous, bottomless segmentation!

How You Can Profit from N-Dimensional Analysis
As I said earlier, I love n-dimensional analysis because it’s so powerful, elegant, simple, and just as there are limitless dimensions you can segment by, there are virtually limitless possibilities for profiting and business optimization. To drive this point home, I wanted to offer another example beyond the remarketing strategy above. In this case, let’s focus on the website experience itself and more specifically, the conversion funnel.

Nearly every website has some form of conversion funnel. And with every conversion funnel comes attrition – visitors who start the process but do not finish it. Take the shopping cart checkout process – one that most of us are probably intimately familiar with by now. With each step of the shopping cart checkout process, you’ll lose visitors. It’s inevitable.

Now, pathing or clickstream reports like those offered in Omniture SiteCatalyst will show you were these people are leaving the process. But because people do not necessarily follow a linear checkout process, any clickstream report may be somewhat misleading because people who diverge from the expected path may end up course correcting and completing the checkout anyway.

For this reason, Omniture offers the Fallout report – which allows you to do “multi-node” funnel analysis. The Fallout report basically ignores the specific paths visitors take, and instead, focuses on key pages that all visitors should touch at some point in a successful visit.

In the shopping cart example, these might include “Add to Cart”, “Billing”, “Shipping”, “Order Confirmation”, and “Thank You”. No matter what path they take, your visitors would have to touch these 5 pages at some point in a successful visit (hypothetically speaking).

So the Fallout report is great for understanding where people bail out at each major milestone in the process. But this still doesn’t tell you why they are bailing out – and that’s where n-dimensional analysis can be incredibly valuable.

With n-dimensional analysis, you can pull up this same fallout report to identify these major attrition points. Once you’ve identified these points, you can add a filter that Excludes all visits with an Order. This means your segment will include all non-ordering visitors.

Now, pull up your Most Popular Pages report and compare this to a successful visit? What are the major differences? Is there one page that people see more often as non-converters than they do as converters? If you’re like most of your peers, you’ll quickly see a page or two that jumps out.

Now, keeping your segment criteria intact, pull up another report that shows any error codes that may have resulted in these visits. Error codes may include form errors, page not found, redirects, authentication issues, etc and are easily captured within SiteCatalyst. Are there any error codes that are particularly prevalent? If so, this represents another great opportunity for improvement. Why are these visitors getting the error page so frequently? Are they new customers trying to create a customer account? Are they from a particular country or state? Perhaps they are all from Canada and your zip code field isn’t accepting their postal code? Or alternatively, are these visitors predisposed to visit the online help section? If so, what help articles are they looking at in particular? What help terms are they searching for? From which specific page are they exiting?

As you might have guessed, each of these questions represents a unique dimension you can filter by to understand why these visitors are unsuccessful in the checkout process. And there are dozens more you can segment by – all depending on the richness of your underlying data set. With n-dimensional analysis, the possibilities are truly limitless.

But wait, how can you do n-dimensional analysis?
Fortunately as an Omniture customer, n-dimensional analysis is just a mouse click away. Omniture Discover offers you the ability to slice and dice your data by any dimension in real-time. If you aren’t already taking advantage of Omniture Discover , be sure to ask your Account Executive or Account Manager how you can. And if you’re not an Omniture customer, but are interested in n-dimensional analysis, please do not hesitate to contact us and we’d be happy to demonstrate Omniture Discover to you.

1 comments
All Keyword Tools
All Keyword Tools

This is very nice. I don't have an idea of this before.it's amazing we can use this strategy for our websites.

I've been focusing keyword research not knowing I can apply this too.