Sign up for our newsletter and get the latest big data news and analysis.

The Power of Indexing

Zach_RhizaIn this special guest feature, Zachariah Sharek of Rhiza discusses the value of creating a data index and how it can be used to glean insights about everything from consumer spending habits to their media habits. Zachariah is senior vice president of product strategy at Rhiza, an online platform pioneering the way marketers and salespeople make Big Data actionable.

We’re living in an age of data-overload.  It takes one second to generate a Google search and one more second to possess endless data on almost any topic imaginable.  The reams of information, statistics and measurements returned can be overwhelming. How do companies begin to navigate the enormous amounts of customer information, like profiles, spending habits and decision-making processes? If that’s not enough, what seems like unlimited amounts of data can be made even more vast by slicing and dicing it to create new measures and data points. All this big data combined with the complexity of modern analytical needs makes it difficult to identify and understand the most impactful insights.

Even after you find insights that are valuable, you’re still not done. You have to quickly, accurately and concisely communicate their value across your organization to gather the support you need to act on those insights. Everyone, not just the data scientists, need to understand data if an organization is going lead with data.

So what is a good way to both uncover valuable insights and communicate them?

How do you keep from drowning in all of that information?

While data visualizations can be a powerful means to communicate data, they do not scale by themselves.  Imagine trying to skim through thousands of bar charts looking for insights!  One very simple technique that can ease analysis and help communicate key insights is the index.

An index is a statistic that quantifies change or comparison across multiple points of data.  To help explain this, let’s make our own version of the Economist’s Big Mac Index.  We want our Big Mac Index to compare the prices of Big Macs across the world to the cost of a Big Mac in the US.

If we wanted to find out how Norway’s prices compare to the United States, the index value is calculated by dividing the Norwegian price for a Big Mac (about $6.30 USD) by the price of a US Big Mac (about $4.80 USD), then multiply by 100 to avoid using decimals:

Rhiza_formula

 

 

This gives us an index value of 131, which we can interpret as a Norwegian Big Mac is 31% more expensive than an American Big Mac.

At its simplest, an index is just a percentage.  However, things become more interesting when we use more complicated measures for the base index. In our example above the base index is the price of a Big Mac in the US. A more complicated base index could be the performance of a target segment compared to the general population: Do women age 25-54 eat more Big Macs than the General Population?

Indexes further simplify analysis by establishing a common reference for all these comparisons, helping analysts communicate findings succinctly and clearly to decision-makers, e.g. “This product’s index is 135 for people aged 18 to 24, which means that it appeals more to younger people than to older.”

Indices become even more powerful when combined together for analysis.   For those in marketing and advertising, a Brand Development Index (BDI) can be used to compare a specific brand’s sales among a particular group to its sales among the general public. This would help identify things like brand performance across market segments or the growth potential of audience segments. Similarly, a Category Development Index (CDI) is used to analyze sales of a specific category of products within a specific group versus the entire consumer base.

Let’s put these two indexes in action: Compare Big Mac sales in cities across the US to each other (BDI) and hamburger sales across cities (CDI).  By plotting the BDI on one axis and the CDI on another, I can easily see which cities consume more hamburger than the average and see how their how well Big Macs do in those markets.  A city with a high CDI index but a low BDI index would represent an opportunity to increase sales amongst a population that is interested in hamburgers.

Despite these capabilities, indexes are often underused in a business’s day-to-day data analysis.  But salespeople, marketers and advertisers alike can easily create and capitalize on indexes. They are a powerful tool to process and analyze data, discover interesting patterns and deduce actionable insights.

An index’s power lies in several factors:

Indexes are easy to read and allow for quick understanding of complex data sets.

Visually, an index is easy to interpret because it represents a distinct comparison. The use of a trend line or table simplifies mass numbers into a digestible format.

Data indexes are efficient, providing context and comparison in a single number.

By clearly delineating one value set versus another, the audience can easily identify the disparities between the two.

Indexes are especially well-suited for making disparate comparisons.

With one glance, even a data novice can make apples-to-oranges contrasts. When a data point is juxtaposed with an index, correlations and insights can jump off the page.

So the next time you’re staring at a data-rich spreadsheet save time by incorporating an index into your data analysis. They can be an elegant solution for finding relevant correlations and demonstrating data-driven insights to a mass audience.

 

Sign up for the free insideBIGDATA newsletter.

Leave a Comment

*

Resource Links: