Customer churn is a major concern for large companies (notably telcos), even in a big data world. Customer retention campaigns are routinely used to prevent churn, but targeting the right customers on the basis of their historical profile is a difficult task. Companies usually have recourse to two data-driven approaches: churn prediction and uplift modeling. In churn prediction, customers are selected on the basis of their propensity to churn in a near future. In uplift modeling, only customers reacting positively to the campaign are considered. Though uplift is better suited to maximize the efficiency of the retention campaign because of its causal aspect, it suffers from several estimation issues. To improve the uplift accuracy, this paper proposes to leverage historical data about the reachability of customers during a campaign. We suggest several strategies to incorporate reach information in uplift models, and we show that most of them outperform the classical churn and uplift models. This is a promising perspective for churn prevention in the telecommunication sector, where uplift modeling has failed so far to provide a significant advantage over non-causal approaches.
Credit card fraud jeopardizes the trust of customers in e-commerce transactions. This led in recent years to major advances in the design of automatic Fraud Detection Systems (FDS) able to detect fraudulent transactions with short reaction time and high precision. Nevertheless, the heterogeneous nature of the fraud behavior makes it difficult to tailor existing systems to different contexts (e.g. new payment systems, different countries and/or population segments). Given the high cost (research, prototype development, and implementation in production) of designing data-driven FDSs, it is crucial for transactional companies to define procedures able to adapt existing pipelines to new challenges. From an AI/machine learning perspective, this is known as the problem of transfer learning. This paper discusses the design and implementation of transfer learning approaches for e-commerce credit card fraud detection and their assessment in a real setting. The case study, based on a six-month dataset (more than 200 million e-commerce transactions) provided by the industrial partner, relates to the transfer of detection models developed for a European country to another country. In particular, we present and discuss 15 transfer learning techniques (ranging from naive baselines to state-of-the-art and new approaches), making a critical and quantitative comparison in terms of precision for different transfer scenarios. Our contributions are twofold: (i) we show that the accuracy of many transfer methods is strongly dependent on the number of labeled samples in the target domain and (ii) we propose an ensemble solution to this problem based on self-supervised and semi-supervised domain adaptation classifiers. The thorough experimental assessment shows that this solution is both highly accurate and hardly sensitive to the number of labeled samples.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.