Target looping using machine learning: an analytical approach using hyper-data in banking

Organizations often use targeting and retargeting strategies to acquire customers. Targeting involves reaching out to an audience based on their demographics, while retargeting persuades potential customers to revisit a website based on their browsing history and online behavior. However, displaying retargeted advertisements can be costly. To address this challenge, we propose a solution called “target looping,” which involves looping decisions back to an intelligent system. This article describes a machine learning model-driven solution that utilizes hyper-data sources such as visitors' online behavior and customer relationship management to optimize advertisement spend. The model generates propensity scores and segments visitors accordingly. Digital marketing teams can then use these segments to drive maximum conversions and optimize cost per acquisition for the millions of monthly visitors to the website.