Real-time bidding campaigns optimization using user profile settings

Abstract

Real-Time bidding is nowadays one of the most promising systems in the online advertising ecosystem. In the presented study, the performance of RTB campaigns is improved by optimising the parameters of the users’ profiles and the publishers’ websites. Most studies about optimising RTB campaigns are focused on the bidding strategy; estimating the best value for each bid. However, our research is focused on optimising RTB campaigns by finding out configurations that maximise both the number of impressions and the average profitability of the visits. An online campaign configuration generally consists of a set of parameters along with their values such as {Browser = “Chrome”, Country = “Germany”, Age = “20–40” and Gender = “Woman”}. The experiments show that, when the number of required visits by advertisers is low, it is easy to find configurations with high average profitability, but as the required number of visits increases, the average profitability diminishes. Additionally, configuration optimisation has been combined with other interesting strategies to increase, even more, the campaigns’ profitability. In particular, the presented study considers the following complementary strategies to increase profitability: (1) selecting multiple configurations with a small number of visits rather than a unique configuration with a large number of visits, (2) discarding visits according to certain cost and profitability thresholds, (3) analysing a reduced space of the dataset and extrapolating the solution over the whole dataset, and (4) increasing the search space by including solutions below the required number of visits. The developed campaign optimisation methodology could be offered by RTB and other advertising platforms to advertisers to make their campaigns more profitable.

Breaking the traditional: a survey of algorithmic mechanism design applied to economic and complex environments

“…The incentive mechanism of design game theory has been widely studied in other fields, such as crowdsourcing sensing and edge computing [ 97 , 162 ]. Furthermore, as a feasible data privacy solution, federated learning has recently been applied in more and more fields, and the framework of federated learning is shown in Fig.…”

The role of perceived usefulness and annoyance on programmatic advertising: the moderating effect of Internet user privacy and cookies

“…So, RTB is a model for computational advertising that uses technologies such as big data (Loebbecke et al, 2020). It is based on the analysis of a massive amount of data generated by cookies from Internet users and it has the ability to identify the characteristics and interests in real time of the target audience viewing each ad impression, thus offering ads that best match the user's interests and optimising their prices through a programmatic auction method (Miralles-Pechu an et al, 2021).…”

A Deep Learning-Based Decision Support System for Mobile Performance Marketing

“…In a few cases, a regression modeling (Reg.) is used (e.g., 12,13 ), where a regression (numeric output) ML algorithm and measure (e.g., RMSE -Root Mean Squared Error) is adopted to model or evaluate a user CTR or CVR class probability (∈ [0.0, 1.0]). We highlight that showing only a predictive CTR or CVR value is not enough to demonstrate the utility of the ML models in their application domain.…”

“…Regarding the ML algorithms, the CTR and CVR prediction tasks have been mostly performed by using models that assume a linear correlation between the input features, 15,6 such as linear Poisson regression 16 and Logistic Regression (LR). 14,13,17 Since 2014, more flexible learning methods were proposed, such as: CTR -Gradient Boosting Decision Trees (GBDT) 14 ; and CVR -GBDT 18 and Random Forest (RF). 6,13 Due to the remarkable success of deep learning in several competitions (e.g., computer vision, natural language processing) 19 , these models were recently proposed for CTR 15,20,11,8,21 and CVR 7,22,21 prediction, under distinct learning architectures: ResNet and Convolutional Neural Networks; 11 deep multilayer perceptrons; 15,20 and Entire Space Multi-Task Model.…”

“…14,13,17 Since 2014, more flexible learning methods were proposed, such as: CTR -Gradient Boosting Decision Trees (GBDT) 14 ; and CVR -GBDT 18 and Random Forest (RF). 6,13 Due to the remarkable success of deep learning in several competitions (e.g., computer vision, natural language processing) 19 , these models were recently proposed for CTR 15,20,11,8,21 and CVR 7,22,21 prediction, under distinct learning architectures: ResNet and Convolutional Neural Networks; 11 deep multilayer perceptrons; 15,20 and Entire Space Multi-Task Model. 7 Our previous work 9 was the first study that proposed deep learning for mobile performance marketing user CVR prediction.…”