Downloads & Free Reading Options - Results

The prevalence of machine learning (ML) applications in the gambling field have been fueled by an accumulation of customer data and computing power. Industry operators, for example, deploy ML to support a variety of use-cases including recommendation systems, fraud detection, customer churn, and customer relationship marketing. Additionally, regulators and government bodies endorse the use of ML for harm minimization and prevention. Several gambling consumer protection products are powered by ML (e.g., BetBuddy, Neccton, Future Anthem, Mindway AI, etc.) and ML methods have also garnered interest amongst the academic community (for a review, see Ghaharian et al., 2022). While ML provides many benefits, its adoption also presents risk and broader ethical concerns. These may include, for example, bias/fairness in predictions, broken data pipelines, and inappropriate training data and/or methods. It is important that these issues are identified and assessed to guide the future development, use, and governance of ML in gambling. Accordingly, this study seeks to find out: What is known about the potential risks and ethical concerns of machine learning applications in gambling? We will conduct a scoping literature review to address this research question. This review type is best suited to answer broad questions and to collect the breadth of literature on a topic. It also allows flexibility to include a range of articles (including grey literature). We have devised this protocol in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (i.e., the PRISMA-ScR in Tricco et al., 2018). The attached file contains completed PRISMA-ScR checklist items.