The ability to differentiate between in-market shoppers and the rest of an advertiser's target market offers tremendous possibilities for boosting sales and maximizing return on ad spend. These in-market shoppers are incredibly valuable as they:
•Perform 5 times more shopping events
•Initiate 8 times more shopping carts
•Are 6 times more likely to make a purchase than when not in-market
Recognizing ready-to-buy shoppers is, however, not an easy task. To do so, companies need access to a large, rich, and cross-site dataset, predictive algorithms, and a real-time platform capable of processing data, making decisions, and targeting ads. Akamai's white paper, entitled "Ready to Buy: the In-Market Consumer" will help online retailers understand how to attract and make customers of shoppers who are in-market today for your company's products.
Ready to Buy: The In-Market ConsumerTable of Contents
Ready to Buy: The In-Market Consumer. 1Shopping Data Drives Understanding of In-Market Consumers. 1Akamai ADS Predictive Analytics: How they Work. 2The Dynamics of the In-Market Consumer . 2The Akamai ADS Privacy Statement. 3About Akamai ADS For Predictive Segments. 3Ready to Buy: The In-Market Consumer 1 Ready to Buy: The In-Market Consumer 2
Ready to Buy: The In-Market Consumer Akamai's Predictive AnalyticsThere are approximately 140 million online shoppers in the United States Of this Of 140 million online shoppers in In order to pinpoint in-market consumers, Akamai's predictive analytics consist of two group, the target market for any given product generally falls somewhere in the range the US, an in-market audience for an parts - model training and model scoring. of tens of millions of shoppers. This is the audience online advertisers typically try to advertiser's products, at any one time, reach to create awareness and consideration for their brand and/or product offering. ranges from tens of thousands to Model training consists of building a predictive model based on a historical data set Targeting for these objectives often uses a combination of display advertising tactics hundreds of thousands of shoppers. of user shopping behaviors. Each model should be customized to the specific transac-such as user demographic data, website contextual information, and traditional tions an advertiser wishes to drive. behavioral targeting. By analyzing the historical data, these models learn - across thousands of different But while the target market is important, there are many advertisers who are specifi- shopping behavioral variables - how consumers act when they are nearing the target cally focused on trying to reach the subset of their target market that is in-market for transaction. The models determine which variables are most important to the particular what they sell right now. The in-market group is the tens of thousands to hundreds transaction in question, and how to combine these variables into a scoring calculation of thousands of shoppers within the target market who are ready to make a purchase that achieves the best predictor of behavior. Every model is unique.in the very near future and require a different set of data-driven targeting tactics. What should be noted is that, typically, no single variable ends up being weighted more than about one-tenth of the overall score - meaning there is no single data No single variable accounts for more Shopping Data Drives Understanding of point that predicts shopping behavior with consistency. Generally, the best predictors include a long tail of variables, reflecting the inherent complexity of modeling human than roughly 10% of a model's score In-Market Consumers behavior. So, for example, knowing that someone put a surfboard in their shopping - as such, there is no single data cart in the last 24 hours is not enough to accurately predict that they are likely to pur- point that can consistently predict The world of direct marketing has long proven that the best predictor of future shop-ping behavior is past shopping behavior. It is upon this premise that Akamai has built a chase that surfboard. On the other hand, knowing that they had also recently booked shopping behavior.
large online shopping data co-op which is made up of anonymous shopping behavioral a trip to Hawaii and purchased a wetsuit substantially increases the likelihood of a near-data from across over 500 consumer shopping websites from virtually every shopping term surfboard purchase.category. With over 6 billion shopping events seen across nearly every online U.S. 100%consumer, Akamai is in a unique position to understand and identify the in-market audience segment.
In-Market 12.7%
7.6%Target 6.9%l 6.5%edMarket o 5.8%M ot 4.7% nEvery U.S. 4.3%oitubOnline Shopper 3.5% 3.2%irt 2.8%n 2.6%oC t 1.4%n 1.2%e 1.1%creP 1 2 3 4 5 6 7 8 9 10 11 12 13 14Variables Contributing to Model
For o... [download for more]
