AI/ML

AI at a CPG Company

  • Posted: April 19, 2024

Colgate-Palmolive reveals how AI helps them achieve key objectives and improve processes. They  provided insights into the use of AI in marketing at AUDIENCExSCIENCE as well as MSI’s Summit 2024.

Read more »

Driving Greater Campaign Reach and Relevancy Across Formats

Driving Greater Campaign Reach and Relevancy Across Formats

Sharmilan Rayer – GM, Amazon Publisher Cloud


Sharmilan Rayer of Amazon Publisher Cloud discussed an approach to empowering addressability as legacy identifiers (cookies and mobile IDs) fade. This approach, called durable addressability, includes the sharing of first-party signals across publishers, advertisers and third parties. Its three pillars are first-party signal investment, secure signal collaboration and machine learning (ML) powered modeling. The Amazon Marketing Cloud is their new advertiser clean room which takes this approach. It allows advertisers to combine their first-party signals with Amazon’s publisher ones and any third-party’s in a privacy compliant way. Key takeaways:
  • Durable addressability starts with each member investing in first-party data from a resource, funding and technology perspective.
  • Sixty percent of advertisers report planning to leverage first-party data for ad placements, and 47% of publishers say their first-party data is the answer to cookie deprecation.
  • The first-party data advertisers would bring to this strategy includes customer engagement, conversions and proprietary audiences.
  • Amazon has access to publisher first-party data across CTV, web, mobile and audio. Having access to this first-party data allows for determining which ad opportunities are best for a particular campaign.
  • As cookies deprecate, clean rooms will begin playing a more important role, according to Amazon.
  • Modeling by machine learning has increased reach 20-30% on unaddressable supply, Amazon claims.
  • A new product called Performance Plus combines Amazon Ads signals, advertiser conversion signals and machine learning to generate predictive segments. It has been observed boosting conversions 30-80%.

Member Only Access
OOH Measurement’s Game Has Changed

OOH Measurement’s Game Has Changed

Christina Radigan – SVP, Research & Insights, Outfront

Christina Radigan of Outfront explored the advantages of out-of-home advertising (OOH) and discussed advancements in its measurement techniques. Christina noted that with the loss of cookies and third-party data, contextual ad placement will see a renewed sense of importance, and in OOH, location is a proxy for context, driving content. She further indicated the benefits of OOH citing a recent study by Omnicom, using marketing mix modeling (MMM), which found that increased OOH spend drives revenue return on ad spend (RROAS). This research also highlighted that OOH is underfunded, representing only 4% to 5% of the total media marketplace. Following up on this, Christina pointed to attribution metrics, measuring the impact of OOH ad exposure on brand metrics and consumer behaviors, to demonstrate OOH's effectiveness at the campaign level. Expanding on their work in attribution, she noted changes stemming from the pandemic: Format proliferation and greater digitization, privacy-compliant mobile measurement ramping up (opt-in survey panel and SDK) and performance marketing and measurement becoming table stakes for budget allocations. New measurement opportunities from OOH intercepts included brand lift studies, footfall, website visitation, app download and app activity and tune in. Finally, she examined brand studies conducted for Nissan and Professional Bull Riders (PBR), showcasing the effectiveness of OOH advertising in driving recall, ticket sales and revenue. Key takeaways:
  • MMMs return to the forefront, as models become more campaign sensitive and are privacy compliant (powered by ML and AI).
  • A study from Omnicom, using MMM, found that optimizing OOH spend in automotive increased brand consideration (11%) and brand awareness (19%). In CPG food, optimizing OOH spend increased purchase intent (24%) and optimizing OOH spend in retail grocery increased awareness (9%).
  • OOH now represents a plethora of formats (e.g., roadside ads, rail and bus ads, digital and print) and has the ability to surround the consumer across their journey, providing the ability to measure up and down the funnel, in addition to fueling behavioral research.
  • Key factors for successful measurement in OOH: feasibility (e.g., scale and scope of the campaign, reach and frequency), the right KPIs (e.g., campaign goal) and creative best practices (Is the creative made for OOH?).
  • OOH advertising is yielding tangible outcomes by boosting consumer attention (+49%). Additionally, there has been a notable surge in advertiser engagement (+200%).
  • Ad recall rates in OOH continue to increase (e.g., 30% in 2020 vs. 44% in 2023).

Member Only Access
AUDIENCEXSCIENCE 2024

AUDIENCEXSCIENCE 2024

The ARF’s annual AUDIENCExSCIENCE conference highlighted the most critical audience measurement issues. Through keynotes, panels, debates and rigorously peer-reviewed research presentations, attendees learned about a wide array of new and evergreen industry topics, endemic to our industry changes. World-class thinkers joined us in NYC to share their perspectives on the future of advertising research and measurement, and how tomorrow’s technologies and data trends will impact advertising and media.

Member Only Access
Human Experience: Why Attention AI Needs Human Input

Human Experience: Why Attention AI Needs Human Input

Dr. Matthias Rothensee – CSO & Partner, eye square

Stefan Schoenherr – VP Brand and Media & Partner, eye square

Speakers Matthias Rothensee and Stefan Schoenherr of eye square discussed the need for a human element and oversight of AI. Beginning their discussion on the state of attention and AI, Matthias acknowledge that race for attention is one of the defining challenges of our time for modern marketers. He quoted author Rex Briggs, who noted the "conundrum at the heart of AI: its greatest strength can also be its greatest weakness." Matthias indicated that AI is incredibly powerful in recognizing pattern from big data sets but at the same time there are some risks attached to it (e.g., finding spurious patterns, hallucinations, etc.). Stefan examined a case study using an advertisement for the candy M&Ms, which considered real humans using eye tracking technology and compared it to results using AI. The goal was to better understand where AI is good at predicting attention and where does it still have to optimize or get better. Results from a case study indicated areas for AI improvements in terms of gaze cueing, movement, contrast, complexity and nonhuman entities (e.g., a dog). The static nature of AI (e.g., AI prediction models are often built based on static attention databases) can become a challenge when comparing dynamic attention trends. Key takeaways:
  • Predictive AI is good at replicating human attention for basic face and eye images, high-contrast scenes (e.g., probability of looking at things that stand out) and slow-paced scene cuts where AI can detect details.
  • AI seems unaware of a common phenomenon called the "cueing effect" (e.g., humans not only pay attention to people's faces but also to where they're looking), which leads to an incorrect prediction.
  • AI has difficulties deciphering scenes with fast movements (e.g., AI shows inertia) in contrast to slow-paced scenes where AI excels in replicating human feedback. In this case human feedback is more accurate.
  • AI is more consumed with attention towards contrast (e.g., in an ad featuring a runner, AI gave attention to trees surrounding the runner), whereas humans can decipher the main aspect of an image.
  • AI decomposes human faces (e.g., AI is obsessed with human ears), whereas humans can detect the focal point of a human face. In addition, AI hallucinates, underestimating facial effects.
  • AI has difficulties interpreting more complex visual layouts (e.g., complex product pack shots are misinterpreted).
  • AI is human centric and does not focus well on nonhuman entities such as a dog (e.g., in scenes where a dog was present, AI disregarded the dog altogether).
  • AI tends to be more static in nature (e.g., AI prediction models are often built based on static attention databases), which can be a problem when comparing this to dynamic attention trends.

Download Presentation

Member Only Access
AI Driven Video Formats Drive Results for Brands

AI Driven Video Formats Drive Results for Brands

Tori Kang – YouTube Specialist, Google

Danielle Perrella – Head of Measurement, Google

Tori Kang and Danielle Perrella from Google talked about AI from a media and video perspective with a summary of the overall landscape and an examination of how AI delivers on its promise in the ways it is working within Google’s YouTube. Tracing video’s effectiveness through the consumer funnel, Tori noted how the accelerating consumer complexity in viewing habits requires marketers to be more agile in navigating audience fragmentation, and AI’s capabilities are able to do the heavy lifting by saving time, optimizing efficiency and improving performance. Danielle illustrated how Google’s AI mechanism, Video Reach Campaigns, measured up against manually optimized campaigns and traditional YouTube formats in comparing ROAS and incremental sales. Key takeaways:
  • In improving reach and efficiency compared to manually optimized YouTube video campaigns, a Bubly case study showed using AI delivered 33% more reach at a 64% lower CPM.
  • Implementing AI earned an average ROAS 3.7x (+271%) higher than, and drove more than double the incremental sales (+111%) of, manually optimized YouTube video campaigns.
  • Identifying areas for optimization by finding inefficiencies, defining how AI can answer critical business questions and evaluating how AI can improve key metrics are the key questions for considering how AI should be integrated into a media plan.
 

Download Presentation

Member Only Access
Business Outcomes in Advertising Powered by Machine Learning

Business Outcomes in Advertising Powered by Machine Learning

Brett Mershmann – Sr. Director, Research & Development (R&D), NCSolutions

Brett Mershmann’s (NCSolutions) discussion focused on how to quantify incremental advantages of some more modern contemporary machine learning (ML) frameworks, over more traditional measurements for incrementality. Beginning the presentation, Brett provided an overview of both traditional modeling techniques as well as more contemporary ML campaign measurements. To understand the differences, Brett detailed an 11-experiment process, using real observational household data, intersected with real campaign impression data but with simulated outcome and with a defined outcome function. The experiments measured accuracy, validity and power. Additionally, they compared ML with randomized controlled trials (RCTs), noting that RCTs are the gold standard but are not always feasible. To accomplish this, they ran both an RCT and an ML analysis, by creating test-control groups on real, limited data. This experiment applied the same outcome function to each, depending on a larger set of variables. In closing, Brett shared feedback from these experiments, which supported ML as a powerful method of measurement and a viable alternative to RCTs. He highlighted the importance of getting the correct data into these models for optimum results. Key takeaways:
  • A survey from the CMO Council indicated that 56% of marketers want to improve their campaign measurement performance in the next 12 months.
  • Traditional campaign measurement techniques use household matching (Nearest-Neighbor), household matching (Propensity) and inverse propensity weighting (IPW), based on simple statistical models applied uniformly. This method simulates balanced test and control groups to estimate the group-wise counterfactual.
  • The ML measurement technique, using NCSolutions’ measurement methodology, is computationally robust for large, complex data sets, understanding that data is not one-size-fits-all and estimates counterfactual for individual observations.
  • Simple A/B testing does not capture the true effect, while the counterfactual approach uses a "what-if model" approach to estimate the true effect.
  • The experiments comparing ML to traditional methods, measuring accuracy, validity and power showed that:
    • Accuracy: Machine learning outperforms on accuracy 55% compared to inverse propensity weighing (9%), propensity match (27%) and nearest-neighbor match (8%).
    • Validity: Percentage of scenarios with true effect in confidence interval (validity) found that ML gave valid estimates most often (91%), compared with inverse propensity weighing (82%), propensity match (64%) and nearest-neighbor match (73%).
    • Power: Machine learning is more statistically powerful. The average width of confidence interval using machine learning was 1.48, compared to inverse propensity weighing (1.56), propensity match (1.78) and nearest-neighbor match (1.72).
  • Results from ML vs. RCTs: Both ML and RCT are accurate in campaign measurement, both methods are generally valid, but ML is more powerful.
    • Overall, ML can be an adequate substitute for RCTs providing meaningful estimates when running an RCT is not a possibility.

Download Presentation

Member Only Access
The Power of AI for Effective Advertising in an ID-free World

The Power of AI for Effective Advertising in an ID-free World

Rachel Gantz – Managing Director, Proximic by Comscore

Amidst heightened regulations in the advertising ecosystem, Rachel Gantz of Proximic by Comscore delved into a discussion of diverse AI applications and implementation tactics, in an increasingly ID-free environment, to effectively reach audiences. Rachel highlighted signal loss as a "massive industry challenge," to provide a framework for the research she examined. She remarked that the digital advertising environment was built on ID-based audience targeting, but with the loss of this data and the increase in privacy regulations, advertisers have placed their focus on first-party and contextual targeting (which includes predictive modeling). In her discussion, she focused on the many impacts predictive AI is having on contextual targeting, in a world increasingly void of third-party data, providing results from a supporting experiment. The research aimed to understand how the performance of AI-powered ID-free audience targeting tactics compared to their ID-based counterparts. The experiment considered audience reach, cost efficiency (eCPM), in-target accuracy and inventory placement quality. Key takeaways:
  • Fifty to sixty percent of programmatic inventory has no IDs associated with it and that includes alternative IDs.
  • Specific to mobile advertising, many advertisers saw 80% of their IOS scale disappear overnight.
  • In an experiment, two groups were exposed to two simultaneous campaigns, focused on holiday shoppers. The first group (campaign A) was an ID-based audience, while the second group was an ID-free predictive audience.
    • Analyzing reach: ID-free targeting nearly doubled the advertisers’ reach, vs. the same audience, with ID-based tactics.
    • Results from cost efficiency (eCPM): ID-free AI-powered contextual audiences saw 32% lower eCPMs than ID-based counterparts.
    • In-target rate results: Significant accuracy was confirmed (84%) when validating if users reached with the ID-free audience matched the targeting criteria.
    • Inventory placement quality: ID-free audience ads appeared on higher quality inventory, compared to the same ID-based audience (ID-free 27% vs. ID-based 21%).

Download Presentation

Member Only Access
« Prev Next »