Digital marketing is a profitable business generating annual revenue over USD 200B and an inter-annual growth over 20%. The definition of efficient marketing investment strategies across different types of channels and campaigns is a key task in digital marketing. Attribution models are an instrument used to assess the return of investment of different channels and campaigns so that they can assist in the decision-making process. A new generation of more powerful data-driven attribution models has irrupted in the market in the last years. Unfortunately, its adoption is slower than expected. One of the main reasons is that the industry lacks a proper understanding of these models and how to configure them. To solve this issue, in this paper, we present an empirical study to better understand the key properties of user-paths and their impact on attribution models. Our analysis is based on a large-scale dataset including more than 95M user-paths from real advertising campaigns of an international hoteling group. The main contribution of the paper is a set of recommendation to build accurate, interpretable and computationally efficient attribution models such as: (i) the use of linear regression, an interpretable machine learning algorithm, to build accurate attribution models; (ii) user-paths including around 12 events are enough to produce accurate models; (iii) the recency of events considered in the user-paths is important for the accuracy of the model.

The goal of digital marketing is to connect advertisers with users that are interested in their products. This means serving ads to users, and it could lead to a user receiving hundreds of impressions of the same ad. Consequently, advertisers can define a maximum threshold to the number of impressions a user can receive, referred to as Frequency Cap. However, low frequency caps mean many users are not engaging with the advertiser. By contrast, with high frequency caps, users may receive many ads leading to annoyance and wasting budget. We build a robust and reliable methodology to define the number of ads that should be delivered to different users to maximize the ROAS and reduce the possibility that users get annoyed with the ads’ brand. The methodology uses a novel technique to find the optimal frequency capping based on the number of non-clicked impressions rather than the traditional number of received impressions. This methodology is validated using simulations and large-scale datasets obtained from real ad campaigns data. To sum up, our work proves that it is feasible to address the frequency capping optimization as a business problem, and we provide a framework that can be used to configure efficient frequency capping values.