This work investigates online purchasers and how to predict such sales. Advertising as a field has long been required to pay for itself—money spent reaching potential consumers will evaporate if that potential is not realized. Academic marketers look at advertising through a traditional lens, measuring input (advertising) and output (purchases) with methods from TV and print advertising. Online advertising practitioners have developed their own models for predicting purchases. Moreover, online advertising generates an enormous amount of data, long the province of statisticians. My work sits at the intersection of these three areas: marketing, statistics and computer science. Academic statisticians have approached the modeling of response to advertising through a proportional hazard framework. We extend that work and modify the underlying software to allow estimation of voluminous online data sets. We investigate a data visualization technique that allows online advertising histories to be compared easily. We also provide a framework to use existing clustering algorithms to better understand the paths to conversion taken by consumers. We modify an existing solution to the number-of-clusters problem to allow application to mixed-variable data sets. Finally, we marry the leading edge of online advertising conversion attribution (Engagement Mapping) to the proportional hazard model, showing how this tool can be used to find optimal settings for advertiser models of conversion attribution.