Look-AI-Like Marketing

Lookalike marketing modeling isn’t new, lookalike modeling utilizing AI, however, is. Lookalike modeling has been a mainstay of the ad tech industry for years, and it has been used to help advertisers expand digital audiences while maintaining relevancy of targeting. The principle is simple, brands want to attract new visitors to their site. What better way to do this than to identify prospects who resemble existing visitors (or customers)? What is new, however, is the dazzling variety of ways in which today's digital marketers are deploying lookalike modeling techniques to enhance the return on investment across marketing channels—both online and offline.

With more data than ever before on a customer's journey, increased adoption of platforms (like customer data platforms and data management platforms) to centralize and analyze that data, and growing ubiquity of ML tools and techniques, lookalike modeling is breathing new life into old channels. Customer-centric businesses have long recognized that the best way to acquire new visitors is to focus on users who resemble their existing customers (or better yet, high-value customers). For digital marketers looking to drive traffic and conversions, this means identifying and purchasing media against audiences based on a small number of static demographic attributes. Your recent site visitors are statistically more likely to be females, aged 29-35? Perfect—serve display advertisements to similar audiences elsewhere on the web.

The problem is that demographic segment-based targeting, while enabling advertisers to reach audiences at scale, isn’t a great proxy for relevancy. Women aged 29-35 are a diverse demographic, only a subset of whom are likely to be interested in a brand’s offering. As a result, performance can tend to show a steep drop-off as audience size increases. Enter lookalike modeling, a form of statistical analysis that uses machine learning to process vast amounts of data and seek out hidden patterns across pools of users. Lookalike modeling works by identifying the composition and characteristics of a ‘seed’ audience, and identifying other users who show similar attributes or behaviors. By analyzing not just demographic but behavioral similarities—e.g., users who have demonstrated similar browsing patterns—lookalike modeling enables advertisers to leverage powerful and complex data signals to find the perfect audience.

Lookalike modeling is a trusty tool in the digital media arsenal—and it’s quickly becoming indispensable to other channels as well. The convergence of ad tech and CRM has made it possible to build lookalike audiences of unprecedented sophistication. AI and machine learning can add even more sophistication to the process, including contextual, geo-location, social, and perhaps even emotional data.

With a single source of customer data spanning online and offline engagement, a brand can unify disparate signals of purchase intent from many customer touch points, including onsite and transaction behavior, email engagement, offline purchases, app usage, call center contacts, product reviews and more. This provides a rich and highly accurate view of the customer. 

Lookalike audiences can be found on social

Facebook Lookalike Audiences enables marketers to build a seed list based on pixel audiences (e.g., users who have recently visited the site or browsed a particular page) or a custom list of users. For example, a fashion retailer “could use a platform to identify all customers with a predicted affinity—based on dozens of behavioral data points — for haute couture, and simply transfer that audience directly to Facebook. Marketers can then indicate how targeted vs. broad they would like the lookalike targeting to be.

For search, getting in front of high-potential prospects when they’re in-market — searching or doing price comparison for a relevant category — is every marketer’s dream. The introduction of Similar Audiences through Google Customer Match enables marketers to automatically optimize bidding strategies around key lookalike audiences.

In the first quarter of 2019, LinkedIn also added lookalike marketing to its offerings. After a year of beta testing, LinkedIn added lookalike audiences to its ads. If someone searched for an article on digital marketing trends, that would map them to a category of being interested in marketing.

Adobe’s Audience Manager can now subtract traits in a lookalike model and report impressions by user segment. Lookalike models are often developed from the attributes of a group of users a brand wants to find more of. A model of the common attributes of the best customers, according to this thinking, can help find other users with similar attributes, who are more likely to become customers of this particular product or service. One problem, Adobe says, is that when a brand creates a model from attribute data — either the brand’s own data or third-party data from a provider — there might be attributes that could bias the model in the wrong direction. For instance, the attributes creating the model might include visits to the brand’s site or other specific sites, when those site visits aren’t useful for finding lookalike users. The new Trait Exclusion capability lets marketers remove selected traits, and it employs Adobe’s Sensei machine learning to help make the subtraction. In addition to removing traits that don’t add value, like site visits, Adobe said the new feature helps marketers focus on influential traits. When the brand has to comply with specific privacy regulations, the model can exclude certain demographic attributes.