Coffee with Michael and Tom Episode 2 - NRP

Coffee with Michael and Tom Episode 2 - NRP

Tom Weiss, Thu 23 July 2020

This week, Michael and Tom discuss the National Representative Panel (NRP). They start by outlining the problem: customers come full of praise about the new Inscape Smart TV or the set-top-box (STB) datasets, but they find them skewed by varying degrees.   To use the data for measurement, we need to find a solution.   Active panels, such as those managed by Nielsen, address skew  e.g., an under-representation of African-American representation, by simply recruiting more African-Americans. Passive panels such as those populated by data collected from consumer devices cannot recruit specific households, and so we need to weight households to address skew.

Dativa's data science consulting team has created a new product known as NRP to address the skews in the Inscape Smart TV  datasets by assigning a weight to each TV household. So if there is a lack of data about Hispanic viewers, Dativa increases the weight assigned to the Hispanic viewers the dataset does contain. 
As other platforms have their methods for dealing with skews,  Michael asks why advertisers would particularly benefit from using Dativa's new NRP product. The main answer is transparency.   NRP is based on a completely transparent methodology.   A second issue is focus.   Dativa is working to make the best weighting system possible.  Michael thinks we are probably putting a bit more into it than others.  Dativa can also create customized weights, so firms can compare their datasets with Inscape datasets. Transparency allows companies and their partners to see what has been taken care of in the datasets and where weaknesses still exist.    
The pair then discuss the use cases where it makes most sense to apply the NRP. These cases include any measurement use cases, and particularly attribution, and measuring uplift of sales. For things like retargeting, NRP isn't necessary. 
NRP is easy to use and works in the same way as say panel data from Nielsen. New privacy laws, and particularly CCPA, which allow people to opt-out of having their data stored, creates challenges.   Opt outs need to be removed from the panel going forward, as well as all previous iterations of the panel. As a result, Dativa has to recalculate new weights weekly - for current and past iterations - to ensure the panel remains accurate while respecting the rights of those who have just opted-out. 

Need help? Get in touch...

Sign up below and one of our data consultants will get right back to you

Other articles about Coffee

Deductive is a global consulting firm providing data consulting and engineering services to companies that want to build and implement strategies to put data to work. We work with primary data generators, businesses harvesting their own internal data, data-centric service providers, data brokers, agencies, media buyers and media sellers.

145 Marina Boulevard
San Rafael
California - 94901
+1 (415) 843 1774

Registered in Delaware

Thames Tower
Station Road

Registered in England & Wales, number 8170657