Analytics Accelerator Case Study

Packing the Home Theater: What Data Analytics Shows Us About Audience Reach

Objective

Fox Entertainment is an American television production company owned by Fox Corporation. They oversee Fox Alternative Entertainment, Bento Box Entertainment, and Tubi, Fox Entertainment’s video-on-demand service. Fox Entertainment sought to establish an analytical framework for expanding their knowledge of data analytics throughout the organization. They aimed to become less dependent on third-party analytics vendors, develop processes for building in-house analytics capabilities, and to deepen the company’s platform analytics to inform its digital media business.

In pursuit of these goals, Fox Entertainment partnered with Wharton AI & Analytics for Business. They worked with a team of faculty-led students to create a new marketing mix model and social media approach for optimizing strategies to increase viewership of television premieres.

Approach

FOX Entertainment provided a series of data sets consisting of campaigns (television shows) with different variables, campaign-level promo data, and campaign-level social media data for fifty days leading up to the television premiere for each campaign.

The team started by cleansing the data, and then performing exploratory data analysis, unsupervised learning, and supervised learning/modeling. They sought a model to optimize advertising across each platform in order to generate the optimum number of viewers for the amount of money spent. This includes the Fox Entertainment Channel itself, all the synergy platforms, paid advertising off-network, and its non-linear digital media platforms. The team analyzed campaign, channel, and awareness effects to determine an appropriate marketing mix.

Regarding social media branding, the team’s initial exploratory data analysis found interesting insights, but did not yield actionable conclusions. Rather than beginning with the data, the team pivoted to begin trying to answer business questions that might be valuable to Fox Entertainment. This process did uncover a number of actionable insights.

Recommendations

Using unsupervised learning and supervised learning/modeling, the Analytics Accelerator team was able to arrive at a number of valuable conclusions and recommendations for Fox Entertainment, including the following:

  • NFL premieres are significant: if Fox Entertainment wishes to reduce advertising spend, they can still ensure strong viewership by placing premieres immediately after NFL games – this is especially true for dramas, a genre that typically sees conversion rates decline without an NFL game preceding it. NFL premieres outperform non-NFL premieres by almost 100%.
  • Paid media provides the best ROI: paid media is simply the most critical metric for increasing program premiere reach, as compared to synergy channels
  • Play balltelevision promos that appeared on sports channels had the highest reach
  • Bring on the drama: drama is the top-performing genre for both new and existing audiences, while comedy-animation campaigns perform well on Facebook
  • Plan ahead: social media reach is highest on Friday and engagement steadily increases over the weekend, peaking on Sunday
  • Paid media provides the best ROI: paid media is simply the most critical metric for increasing program premiere reach, as compared to synergy channels
  • Play balltelevision promos that appeared on sports channels had the highest reach
  • Bring on the drama: drama is the top performing genre for both new and existing audiences, while comedy-animation campaigns perform well on Facebook
  • Plan ahead: social media reach is highest on Friday and engagement steadily increases over the weekend, peaking on Sunday

About the Analytics Accelerator

Every fall and spring semester, Analytics at Wharton hosts the Analytics Accelerator, an experiential learning program that pairs students with a company to solve a real-world business problem using the company’s actual datasets and the latest techniques including machine learning and AI.

Learn More