Machine Learning in Financial Decision-Making: Predicting User Purchases Through Web Engagement Metrics

Web Analysis has proven itself to be a valuable tool in aiding online businesses to thrive in this modern era. It allows businesses to understand consumer behaviour, optimize user experiences, and enhance website performance. This paper explores the development of a predictive machine learning model that integrates web KPIs and UI/UX design elements to forecast user purchasing behaviour on e-commerce platforms. Web analytics is a critical tool for understanding consumer interaction and optimizing website performance. It faces limitations in addressing complex datasets and dynamic user patterns. This research seeks to enhance predictive accuracy by combining metrics such as bounce rate, conversion rate, session duration, and scroll depth with design elements like light and dark theme. The proposed model is trained on historical user interaction data that will be evaluated across various machine learning techniques to determine the most effective approach. The findings aim to bridge the gap between web KPIs and user experience in predictive modelling to offer actionable insights for improving website engagement and driving business outcomes in the competitive digital marketplace.