Multi-Click Attribution in Sponsored Search Advertising: An Empirical Study in Hospitality Industry
Anderson, Chris K.; Cheng, Ming
Sponsored search advertising has become a dominant form of advertising for many firms in the hospitality vertical, with Priceline and Expedia each spending in excess of US$2 billion in online advertising in 2015. Given the competition in online advertising, it has become essential for advertisers to know how effectively to allocate financial resources to keywords. Central to budget allocation for keywords is an attribution of revenue (from converted ads) to the keywords generating consumer interest. Conventional wisdom suggests several ways to attribute revenues in the sponsored search advertising domain (e.g., last-click, first & last-click, or evenly distributed approach). We develop a multi-click attribution methodology using a unique multi-advertiser data set, which includes full advertiser and consumer-level click and purchase information. We add to the literature by developing a two-stage multi-click attribution methodology with a specific focus on sponsored search advertising in the hospitality industry with which we develop a parametric approach to calculate the value function from each stage of the estimation process. Given our multi-advertiser data set, we are able to illustrate the inefficiency of single-click attribution approaches, which undervalue assist clicks while overvaluing converted clicks.
sponsored search advertising; attribution modeling; choice model; hospitality industry
Required Publisher Statement: © Cornell University. Reprinted with permission. All rights reserved.