Media Innovation Group (MIG)

Conversion attribution modeling across the purchase funnel

Published on 27-Dec-2011

Validated on 07 Oct 2013

"Netezza’s data warehouse appliance enables us to synthesize data across multiple media channels through ZAP and optimize campaigns to efficiently achieve our clients’ goals." - Brian Lesser, VP and General Manager,Media Innovation Group

Media Innovation Group (MIG)

Media & Entertainment

Deployment country:
United States

Data Warehouse, Information Infrastructure


Media Innovation Group’s Zeus Advertising Platform (ZAP) helps brand advertisers to track the effectiveness of each digital marketing element in the purchase funnel, and identify which factors affect their audience, at what times, and if/how they lead to conversion. Powered by the IBM Netezza data warehouse appliance, ZAP collects, stores and analyzes over 13 months of historical user-level data to help advertisers optimize campaigns and lower the cost per acquisition.. This insight helped one bank achieve 25 percent higher conversations with a 33 percent lower cost per acquisition.

Business need:
Inability to track elements of campaign success during awareness and consideration phases of purchase funnel. Difficult to get a single, comprehensive view of all activity across campaign, advertiser, brand and channel at the user level

Cost-efficient, scalable platform supports collection and analysis of every advertising data element leading to conversion at the user level

Hundreds of millions of unique users tracked per month for many simultaneous campaigns; banking client achieved 25 percent higher conversions with 33 percent lower cost per acquisition

Case Study

Marketers face a consistent challenge in determining how to get maximum influence from minimal dollars in order to convert “decision makers” into buyers. To achieve this goal, marketers need to understand how their advertising efforts are contributing to their clients’ bottom line. Conventional attribution in digital media credits the last click before a sale with 100 percent of the revenue produced by the conversion.

However, substantial independent research has proven that early funnel exposures have a significant impact on the likelihood of a conversion. Marketers using last click attribution risk dramatic under-optimization of essential campaign elements that funnel users through the conversion process. Online marketers and agencies therefore attempt to diligently track and analyze all of the elements in the marketing mix that are effective in driving customers to purchase. However, the ever-expanding array of digital marketing channels and consumer touch points makes tracking all of the relevant data a daunting challenge. Gaining unique insights from terabytes of user-level data requires a new strategic approach and the production of a powerful new platform combined with a fundamental technology breakthrough in data warehousing.

Problem solved: Media Innovation Group’s Zeus Advertising Platform (ZAP)
Media Innovation Group (MIG) is the WPP Group’s digital nerve center, providing ad management technology, media network services, search marketing technology, and innovative media management products and services. Media Innovation Group is solely dedicated to developing innovative new products and custom solutions for media investment companies like GroupM (largest media investment management operation within WPP) and its agencies. Zeus Advertising Platform is one of the cornerstone products created by MIG.

ZAP solves the accountability problem faced by all media agencies and advertisers. ZAP allows leading brand advertisers within Mindshare, MEC, MediaCom and other agencies to track the effectiveness of each individual digital marketing element in the purchase funnel, to identify precisely which factors affect their audience at what times, and if/how they ultimately lead to conversion. ZAP provides a holistic view of site analytics and campaign data for a comprehensive understanding of every individual consumer.

How does ZAP do it? Why can’t others match its capabilities?
Before MIG’s innovative ZAP solution built upon the IBM fundamental technology breakthrough, solving the conversion attribution problem would have required costly and complex customization of traditional data warehouse technologies in an attempt to squeeze performance out of legacy approaches to terabyte-scale data analysis. Flexibility of analysis would have been severely limited by the need to aggregate and index data in anticipation of a finite set of reporting options. Accuracy of analysis would have been sacrificed due to the need to sample subsets of the relevant data and utilize only the most recent data history in order to cut down on storage and performance costs.

MIG, on the other hand, uses the IBM Netezza data warehouse appliance’s unique capabilities to solve this problem in a way that was previously not possible. ZAP doesn’t limit its analysis to sampled subsets of recent data. It collects and stores over 13 months of historical user-level data and draws from it to provide complex and robust analysis. IBM’s scalable yet cost-effective data warehouse appliance supports the massive and increasing data volumes ZAP collects from a variety of sources, including DART, Atlas, and more.

In order to manage such large volumes of data, Media Innovation Group needed to select a data warehouse provider to be the foundation upon which ZAP would be built. Before deciding to go with Netezza, MIG also evaluated offerings from other leading providers of data warehouse technologies. The IBM Netezza data warehouse appliance came out on top due primarily to its price/performance ratio and ability to scale up and out with linear performance gains.

The IBM Netezza data warehouse appliance provides Media Innovation Group with a high-performance, scalable, simple and cost-efficient platform that allows the company to analyze a broad spectrum of granular information over long periods of history through ZAP. This allows it to better understand and evaluate every advertising element that drives movement through the purchase funnel.

Accountable advertising at last
Through ZAP, MIG is currently tracking the effectiveness of every single advertising element within many live campaigns that reach hundreds of millions of unique users per month, and the solution is expanding in both data volumes and capabilities. ZAP enables robust analysis of campaigns and allows clients to gain actionable insight from granular data. Clients can measure the effectiveness of any and every variable in a campaign including site selection, placement, creative, format, time, campaign cost and return on investment (ROI). Using this data, clients can create proper attribution models and understand what leads to conversions going beyond the ‘last click.’ These insights provide unparalleled advertising targeting capabilities and campaign lift to Media Innovation Group’s clients.

ZAP’s robust user-level data aggregation enables clients to see user interaction across not just one campaign, but across multiple campaigns and brands. This complete view of user interaction is unique to the ZAP solution. Also, only with ZAP technology can clients measure the effectiveness of sites and networks based on unique audience, thus providing an understanding of the duplication of audience across these sites. Armed with the robust pool of user-level data, ZAP enables clients to have unique visibility into performance and thus the ability to optimize campaigns to achieve their specific goals.

ZAP client case study examples
One example of the impact ZAP is having on Media Innovation Group’s clients’ advertising campaigns comes from a large bank. During the initial phase of the campaign, the banking client noticed that cost per acquisition (CPA) seemed to increase over the weekend. It considered halting delivery of weekend impressions as these on first glance appeared to cost more. However there was an important unknown factor regarding how much this would impact conversions, and thus overall CPA. A ZAP analysis, possible only with Media Innovation Group’s technology, revealed that those weekend impressions were actually having a substantial positive effect, resulting in a significant amount of conversions during the week. The conclusion was that, even though conversions were lower on the weekends, consumers were in fact viewing the impressions on weekends but would wait until the work week started to actually “take care of business” and open a bank account. If the banking client had indeed stopped running the campaign on the weekends, it would have lost about 25 percent of its total conversions, which were attributed back to the weekend impressions, and at the same time would have catalyzed a 33 percent higher CPA. Armed with the insight from ZAP, the client continued weekend delivery thus maintaining a lower CPA and garnering more conversions.

Another example of the ZAP impact on Media Innovation Group’s clients comes from a leading global automotive manufacturer. The company runs many simultaneous campaigns – some to promote specific car models, some to promote the overall brand and others to offer special discounts. The challenges this automaker faced were its inability to track consumers’ interactivity with multiple campaigns at once and its lack of understanding of advertising campaign effectiveness at an overall level. For example, it could neither determine the effect of one or more campaigns on sales of a particular model, nor could it gain any insight into how those campaigns impacted conversions across various car models.

With ZAP’s custom reporting, the automaker has immediate access to a comprehensive view of all its campaigns and how they’re individually and cumulatively affecting each consumer. The client has access to reporting that is not available in other leading ad serving and reporting tools, such as frequency, conversion by tag, attribution, and more. In order to gather just the portion of ZAP reporting on data elements that are available in the third party ad server it uses, the client would need to spend at least one entire day setting up and pulling reports (30 minutes per standard individual site report) and aggregating the data, in addition to another day or two to analyze and make sense of that data. Even after those laborious tasks were accomplished, the client would still have only a superficial picture of campaign performance according to last view/last click and not the full understanding at the user level that ZAP provides automatically and instantaneously.

Furthermore, the automaker uses ZAP to evaluate whether it is worthwhile to advertise on popular branded third party sites, whose advertising rates are expensive but whose true value to their campaigns was previously unknown.

A leading-edge technology platform
Using its IBM Netezza-powered ZAP solution, Media Innovation Group can analyze the effect of various digital advertising elements very quickly, lending itself to iterative and comprehensive analyses that were not previously feasible or available with any other solution. Media Innovation Group’s ZAP can slice and dice the data in different ways, running multiple models and testing effects of various factors across numerous facets. With the results from these robust analyses, Media Innovation Group can provide clients with valuable, actionable information that they cannot garner elsewhere. This insight in turn enables clients to optimize campaigns in the most effective ways, driving better performance and results. Database administrators spend very little time maintaining the ZAP database to “keep it working,” unlike their counterparts in other organizations that spend the majority of their time tuning their less extensive databases. Instead, Media Innovation Group’s database administrators can focus on more strategic activities that create real value for their clients. And with the ability to store longer data history, Media Innovation Group can conduct attribution modeling to help identify longer term trends and identify the types of specific activities that work with certain audiences, in certain timeframes, without guessing.

Media Innovation Group and Netezza teamed to deliver an unprecedented level of analytics to the advertising industry. In summary, Lesser stated, “Media Innovation Group’s partnership with Netezza is central to our strategy to win the battle for data supremacy!”

About IBM Netezza data warehouse appliances
IBM Netezza data warehouse appliances revolutionized data warehousing and advanced analytics by integrating database, server and storage into a single, easy-to-manage appliance that requires minimal set-up and ongoing administration while producing faster and more consistent analytic performance. The IBM Netezza data warehouse appliance family simplifies business analytics dramatically by consolidating all analytic activity in the appliance, right where the data resides, for industry-leading performance. Visit to see how our family of data warehouse appliances eliminates complexity at every step and helps you drive true business value for your organization. For the latest data warehouse and advanced analytics blogs, videos and more, please visit:

About IBM Data Warehousing and Analytics Solutions
IBM provides the broadest and most comprehensive portfolio of data warehousing, information management and business analytic software, hardware and solutions to help customers maximize the value of their information assets and discover new insights to make better and faster decisions and optimize their business outcomes.

For more information
To learn more about the IBM Data Warehousing and Analytics Solutions, please contact your IBM sales representative or IBM Business Partner or visit:

Products and services used

IBM products and services that were used in this case study.

IBM Netezza Performance Server

Legal Information

© Copyright IBM Corporation 2011 IBM Corporation Software Group Route 100 Somers, NY 10589 U.S.A. Produced in the United States of America December 2011 IBM, the IBM logo, and Netezza are trademarks or registered trademarks of International Business Machines Corporation in the United States, other countries, or both. If these and other IBM trademarked terms are marked on their first occurrence in this information with a trademark symbol (® or ™), these symbols indicate U.S. registered or common law trademarks owned by IBM at the time this information was published. Such trademarks may also be registered or common law trademarks in other countries. A current list of IBM trademarks is available on the Web at “Copyright and trademark information” at Other company, product and service names may be trademarks or service marks of others.