predictive analytics

Improving Viewership Projections: Forecasting for Data-Driven Audience Segments

Diana Saafi, Data Science Lead at Discovery, built on Cliff Young’s comments about the importance of multiple indicators for forecasting. Saafi forecasts linear television audiences in segments of interest to advertisers (beyond age-sex segments), rather than political outcomes. She and her team have found that their models have benefited from using multiple sources of data.  She recommended identifying signals that are most predictive, experimenting with different types of models (such as ARIMA models and AI models), continually refreshing the data in the models, and continually updating the models. While this process is now automated at Discovery, there are people who monitor changes in the predictions, which she referred to as “human-in-the-loop automation.”

COVID-19 FORECAST

Rex Briggs, Founder & Executive Chairman of Marketing Evolution, who had developed forecasts of US COVID infections and deaths early in 2020, before it had been declared a pandemic, talked about the difficulties in “exponential forecasting” of events like a pandemic, compared to “stable state” forecasting of the impact of media, marketing, and creative. Just as companies might not have anticipated the impact of COVID-19 as it spread, they may be caught “flat-footed” in forecasting the exponential decay of the disease as vaccinations spread in 2021.  Business forecasts of the impact of COVID in 2021 should take into account vaccination rates by age and surveys on acceptance of the vaccine.

In Defense of Polling

David Dutwin, SVP of Strategic Initiatives at NORC, and a past president of AAPOR and survey research expert, in an interview with ARF CEO & President Scott McDonald, Ph.D., encouraged the advertising and marketing industry to maintain their faith in survey research. Surveys for marketing and advertising do not have to contend with two problems with election forecasting based on polls:

  1. Unlike market research surveys, pre-election polls are, “measuring a population that doesn’t [yet] exist,” – the population that will vote in an election.
  2. Given that lack of trust in major media is stronger at one end of the political spectrum than the other, non-response to surveys may well be correlated with political opinions but not with the subjects of most media and advertising surveys. Non-response therefore may well be less damaging for market research surveys.

There Were Always Mixed Signals: Triangulating Uncertainty

Cliff Young, President of US Public Affairs at Ipsos, proposed that multiple indicators be used to forecast elections, not just data from the horse-race question alone. In particular, leaders’ approval ratings are strong predictors of their probabilities of winning, and Trump’s approval rating exceeded his horse-race preference in several swing states. Taking this variable and others (incumbency, perceptions of the most important problems facing the country) into account, Ipsos created a model based on results of over 800 elections across the globe. The model had predicted that a narrow Biden win with Republicans retaining control of the Senate was more likely than a Blue Wave.

What Did Pollsters Learn from the 2020 Election Polls?

Kathy Frankovic, a polling export who led the survey unit at CBS News for over 30 years and now consults for YouGov, highlighted two plausible hypotheses for the polling industry’s over-estimation of Democratic strength in the election:

  1. Likely voter models built on past voting practices: Likely voter models were based on the norm of Election-Day voting, and were unprepared for an election in which two thirds of 2020 votes were not cast on Election Day. One to two percent of mail-in votes don’t get counted, but in seven states, about 10% or more are rejected.
  2. The “missing” Trump voter (as opposed to the “shy” Trump voter): In states which Trump carried with 55% or more of the vote, YouGov pre-election polls showed him tied with Biden. Trump’s bashing of the polls may have discouraged his supporters from participating in polls.

The Exploding Complexity of Programming Research, and How to Measure It, When Content is King

Programming researchers are not getting the data they need to make informed decisions and Joan FitzGerald (Data ImpacX) uses streaming’s complex ecosystem to explain the conundrum facing programmers. Key insights into monetization and performance are not supported despite the inundation of new forms of data, leaving programmers without a comprehensive picture of their audience. Together with Michael McGuire at MSA, Joan outlined a methodology funnel that combined 1st, 2nd and 3rd party data to create equivalized metrics that, once leveraged, could meet critical programming research demands.

FORECASTING 2022: How Can Scenario Planning Improve Agility in Adjusting to Change?

On July 12, 2022, forecasting, and product experts shared frameworks and strategies for participants to consider as they plan amid disruptions in the industry. Presenters discussed techniques marketers could use to drive consumer action and advocacy — as well as econometric models for search trends, insights on holistic analytics programs, reflections on gold standard probability methods — and new forecasting techniques in the wake of the pandemic and more.

Forecasting Post-Pandemic Business Recovery

At ARF’s DATAxSCIENCE 2021, experts in forecasting and scenario planning presented the latest research and insights on understanding which changes in consumer behavior and attitudes will help shape the post-pandemic recovery. They also shared examples of different research methods and models to tap into these signals. Key themes of the conference included:

  • The fundamentals did not change, and it’s important not to lose sight of the fundamentals that made brands successful.
  • Trends that became accelerated by the pandemic, such as anything related to technology and healthcare, are likely to continue.
  • What drives value may have changed for people.

Optimizing TV Promotion with Data, a Case Study with Warner Bros. Discovery

Warner Brothers Discovery (WBD) worked with Civis Analytics (CA) to optimize their TV programming promotions over 30 U.S. networks that premieres dozens of seasons annually across a diverse linear TV portfolio. Max Schuman explained how CA’s approach blended classic marketing mix model (MMM)’s regression models with machine learning’s (ML) ability to discern relationships that best predict outcomes humans can’t see easily. With a custom model that was able to guide decision-making on several levels—what TV series to promote, how and where to market, and what ROI to expect—WBD used CA’s platform as a starting point for all media decisions throughout the full funnel, inclusive of owned and paid media.