01

Sep

By Alex Poon
2 comments
Assigning Recommendation Values when setting a Front Page

One of the features of our platform that some of our customers are super excited about is our ability to assign a direct monetary value to each of the recommendations we provide for how to set the front page.  Publishers are interested in knowing exactly how much value we add, on top of the value their content is already generating.  In addition, the Recommendation Values help editors in prioritizing which recommendations to take.  Being the data and optimization guy, I of course want them to take all the recommendations all the time.  Realistically, I understand that given the real-time nature of our system, that would be impossible for an editorial team to do except when everything is automated.  With that said, I would like to provide a peek into our Recommendation Value concept and show you how it works.

For each content recommendation in each time period, we assign a value.  This value could be in monetary terms, page views, engagement, or any other metric the media property uses to measure performance.  The Recommendation Value takes into account the specific value of that piece of content, content type, the depth into the site it drives the reader and the monetization methods used by the media property.

Based on the action of the Editorial Team, the Recommendation Value is categorized into either Realized Value or Opportunity Cost (See figure below).  Realized Value is the value captured by the media property by acting on the recommendations.  Opportunity Cost is the potential value loss from not taking the recommendations.  Opportunity Cost comes in two flavors:

  1. the recommendation was ignored or not taken in time
  2. as discussed in an earlier editorial instructions post, editors can put in instructions to shape our recommendations and recommendations prevented by these instructions are counted as Opportunity Cost. For example, if a two-day old Mayor Bloomberg article would generate the most value in the top spot but the editor has decided ahead of time that nothing older than 4 hours can be placed in the top spot, we have traded performance with editorial tone.

We don’t have an opinion on how a media property should set its tone.  We do execute on the publishers tone down to the T and keep track and report on those actions.

Recommendation Value provides full transparency into how the Visual Revenue decision support platform and enables us to clearly communicate the importance of individual recommendation to the editors.

What do you think? What else can we do to support the editorial process while maximizing value?  We would love to hear from you in the comments – or feel free to email us at hello@visualrevenue.com.

  • http://tumbleweedmarketinganalytics.com/ Tumbleweed

    Well, a very interesting look into the Visual Revenue recommendation system, for sure. I assume that the ‘cost’ values assigned to content depend (in the case of media content that is subscription-based) on content prices (eg. .17 cents per article, $4.99 per subscription)? Could your engine help a publisher to identify the ‘opportunity cost’ involved with having different subscription price-points? For example, I ignore your recommendation and place Article A on the home page at one price rather than Article B at another. Can you evaluate which article might maximize subscription revenue?

  • http://visualrevenue.com/ Alex Poon

    We let our customers define their optimization objectives, which is also the cost values. So, as long as our system knows about the different pricing models, we will be able to provide the optimal solution (maximum of whatever we are trying to optimize and in this case, total revenue) within the editorial guideline we were given.