Share with your friends


Analytics Magazine

Analyze This! ‘Attitudinal Targeting’ Aims at Online Marketing

September/October 2010

Vijay MehrotraBy Vijay Mehrotra

A recent article [1] in the Wall Street Journal by Julia Angwin shines a bright light on how unsuspecting individuals’ Web browsing history is being captured and the speed with which this data is being sold to marketers to help their Web advertising. Her discussion of cookies, beacons, data exchanges and personalization reveals just how rapidly the world of online advertising is evolving. After reading such an article, you might be tempted to believe that the online world is on the cusp of the personalization revolution predicted by Stephen Spielberg in the film “Minority Report” [2].

Resist that temptation.

The vast majority of online marketing is direct response – advertising intended to get you to do something right now. While personalizing these ads based on an individual’s Web history or inferred demographic information clearly has some value, there are limits to its effectiveness. These limitations are reflected in the price paid for these bits of personal information, usually just a fraction of a cent each.

On the other hand, the really big money in advertising is spent on so-called brand ads, which do not try to elicit an immediate response but instead try to make an emotional

connection with the viewer. These emotional connections are at the core of the customer relationship and are recognized to have an increasingly large economic impact [3]. This importance is reflected in the amount of money spend on brand ads: in 2010, over 60 percent of the more than $200 billion spent on media advertising will be focused on “branding.”

Promising New Company

Even though the typical consumer spends about 30 percent of her media time surfing the Internet, only 5 percent to 10 percent of budgets for brand advertising are spent online. This disparity suggests that relatively few brand advertisers feel confident that they can reach their desired audience with the desired messages, despite the mountains of tracking data available today. Several branding consultants have been very candid with me in confirming this phenomenon during recent conversations.

Which is why I am so excited about a new corporation I’ll call “The Company” for the purposes of this article. Launched initially as an online advertising network in the public affairs space (think of ads seeking to connect with opponents of gun control or supporters of renewable energy), The Company has developed an analytic methodology called “attitudinal targeting” that seeks to match online brand advertisements to customers based on more intimate personal information than just Web browsing history or simple demographics.

The data foundation for The Company’s attitudinal targeting is an innovative approach to traditional survey research that allow the company to continually collect very large scale waves of data that provides statistically significant insights into much richer personal characteristics from a carefully selected mix of survey participants. Based on this survey data, The Company can describe an audience on seemingly more abstract values-based scales such as “self-esteem,” “eternal life,” “individual freedom” and “respect for future generations” that map directly to the values, beliefs and attitudes that brand advertisers care about. In addition, with the explicit permission of these panelists, The Company also has access to additional information about them, including the details of their online Web browsing history.

From here, based on this proprietary database, The Company uses statistical models to find these richly defined audiences based on the patterns of personal thought that are so prized by today’s brand advertisers. Finally, at the end of this information value chain, The Company’s predictive algorithms quantify how effective particular Web pages are in reaching the desired groups for each of its clients’ advertising campaigns.

Suppose, for example, that you are launching a premium priced healthy food product for children under 10 years old and seeking to build brand awareness among potential future customers. Demographic targeting would search for Web sites that featured a pre-defined target audience of, say, mothers between 25 and 45 with family income above a particular threshold. Behavioral targeting would place its ads on Web sites associated with parenting. Attitudinal targeting with The Company, on the other hand, would identify the specific values and emotional characteristics that the product marketing team had designed the product to embody (for example, strong scores on family relationships, concern for personal health, perceived affluence and unease about childhood obesity), analyze its database to construct a richer profile of the people who share these attributes, and then use its scoring methodology to analytically determine which Web sites to use for this ad campaign. The bottom line: with The Company, brand advertisers can make a product targeted for people with specific values, develop brand messaging to hit upon those key values, and then present this message to people online who share these values.

From an analytics perspective, there is a lot to like about The Company. Rather than relying on mountains of data scraped from cookies and beacons before being packaged and sold in bulk on today’s evolving data exchanges, The Company’s approach systematically gathers the type of data that is needed to support its methodology – with the consent of its panelists. This means that the data that drives its predictive models is more pointed and detailed (with a focus on values, beliefs, and attitudes), more accurate (datasets based on cookies and beacons are often filled with inaccurate information) and less controversial (free from the risk of actual or perceived privacy violations [4]). In addition to its carefully constructed database, the company also seems to have developed some interesting clustering and forecasting methods to translate this raw data into actionable information.

Beyond its analytic innovations, The Company is bringing considerable commitment and creativity to the complex challenge (and huge market opportunity) of providing brand advertisers with a targeted, valuable, and cost-effective platform for communicating with customers online. It will be very interesting to see what the future holds for them, and for their customers’ brand advertising portfolios.

Vijay Mehrotra ( is an associate professor, Department of Finance and Quantitative Analytics, School of Business and Professional Studies, University of San Francisco. He is also an experienced analytics consultant and entrepreneur and an angel investor in several successful analytics companies. He will join “The Company’s” Technical Advisory Board this fall.


3. See for example
4. Privacy is at the center of a very contentious debate about the use of personal information to support targeted advertising. The interested reader can find more on this topic at and at




Using machine learning and optimization to improve refugee integration

Andrew C. Trapp, a professor at the Foisie Business School at Worcester Polytechnic Institute (WPI), received a $320,000 National Science Foundation (NSF) grant to develop a computational tool to help humanitarian aid organizations significantly improve refugees’ chances of successfully resettling and integrating into a new country. Built upon ongoing work with an international team of computer scientists and economists, the tool integrates machine learning and optimization algorithms, along with complex computation of data, to match refugees to communities where they will find appropriate resources, including employment opportunities. Read more →

Gartner releases Healthcare Supply Chain Top 25 rankings

Gartner, Inc. has released its 10th annual Healthcare Supply Chain Top 25 ranking. The rankings recognize organizations across the healthcare value chain that demonstrate leadership in improving human life at sustainable costs. “Healthcare supply chains today face a multitude of challenges: increasing cost pressures and patient expectations, as well as the need to keep up with rapid technology advancement, to name just a few,” says Stephen Meyer, senior director at Gartner. Read more →

Meet CIMON, the first AI-powered astronaut assistant

CIMON, the world’s first artificial intelligence-enabled astronaut assistant, made its debut aboard the International Space Station. The ISS’s newest crew member, developed and built in Germany, was called into action on Nov. 15 with the command, “Wake up, CIMON!,” by German ESA astronaut Alexander Gerst, who has been living and working on the ISS since June 8. Read more →



INFORMS Computing Society Conference
Jan. 6-8, 2019; Knoxville, Tenn.

INFORMS Conference on Business Analytics & Operations Research
April 14-16, 2019; Austin, Texas

INFORMS International Conference
June 9-12, 2019; Cancun, Mexico

INFORMS Marketing Science Conference
June 20-22; Rome, Italy

INFORMS Applied Probability Conference
July 2-4, 2019; Brisbane, Australia

INFORMS Healthcare Conference
July 27-29, 2019; Boston, Mass.

2019 INFORMS Annual Meeting
Oct. 20-23, 2019; Seattle, Wash.

Winter Simulation Conference
Dec. 8-11, 2019: National Harbor, Md.


Advancing the Analytics-Driven Organization
Jan. 28–31, 2019, 1 p.m.– 5 p.m. (live online)


CAP® Exam computer-based testing sites are available in 700 locations worldwide. Take the exam close to home and on your schedule:

For more information, go to