By using website you agree to our use of cookies as described in our cookie policy. Learn More

TDWI Upside - Where Data Means Business

Customer Data Profiling: Persona Analytics (Part 4 of 4)

Now you understand behavioral analytics, and you can distinguish between individuals sharing a single customer account. How can you use this information for business advantage?

Let's say that you have used the advice from the last article to configure your applications to analyze the different meta-characteristics of transaction streams (whether they are Web transactions, mobile device transactions, or actions taken using streaming video applications, among many others).

You can now distinguish between what might be different individuals sharing a single account. How can you use this information for business advantage?

If you recall from Part 2 in this series, when more than one individual is transacting business through the same account, the customer analytics will produce skewed profiles that combine the behaviors of all the personas. This leads to challenges in effectively using those profiles in predictive models for recommendation -- causing missteps such as recommending children's books to adults, dog toys to a cat lover, or diapers to a 10-year-old.

The objective of persona disambiguation is to differentiate the different personas and configure the analytics applications to deliver recommendations and suggestions customized to each one.

For example, let's say that your analysis has determined that there are three different viewer personas for your streaming video service: a child persona that interacts in the midafternoon, an adult who views drama in the late prime-time period, and an unknown (potentially an older teen) who watches horror movies in the early morning.

Without persona disambiguation, you might converge all these viewing habits into a single customer profile, and you might make the mistake of suggesting a horror movie to a young child in the middle of the afternoon.

Persona disambiguation can help adjust your customer analytics applications. You can reconfigure your recommendation engine to suggest children's shows in the afternoon, dramas during prime time, and horror movies in the early morning.

From a practical standpoint, persona analytics provides three key capabilities:

  • Determine that there are multiple individuals sharing a single customer account.
  • Differentiate the different personas that are using the account by the characteristics of their interactions.
  • Refine recommendation engines and other predictive analytics applications to focus on each unique persona within the context of each persona's behavior model.

Given these capabilities you can overcome the issues of skewing customer profiles and delivering imprecise analytics results. However, it is also interesting to recognize that each persona can be presented with a reasonable customer experience even if you do not know the exact identity of any of the personas.

In other words, you can differentiate the personas by their behaviors, recognize each persona by its behavioral characteristics, and then tailor your analytics to each individual without needing any additional personal detail!

The challenges of trying to accurately profile overloaded customer accounts will continue to increase as more companies provide services across multiple channels or sell products to multiple individuals within a single household.

As the breadth of each customer account grows, the precision of great service will diminish unless each individual can be provided with a great customer experience. Persona disambiguation and subsequent persona analytics will help to ensure the quality of company-customer interactions.

Articles in this series on customer data profiling:

Part 1: The Precision Problem

Part 2: Problems with Personas

Part 3: Persona Disambiguation and Behavioral Analytics

Part 4: Persona Analytics

About the Author

David Loshin is a recognized thought leader in the areas of data quality and governance, master data management, and business intelligence. David is a prolific author regarding BI best practices via the expert channel at BeyeNETWORK and numerous books on BI and data quality. His valuable MDM insights can be found in his book, Master Data Management, which has been endorsed by data management industry leaders.

TDWI Membership

Accelerate Your Projects,
and Your Career

TDWI Members have access to exclusive research reports, publications, communities and training.

Individual, Student, and Team memberships available.