A systematic data-driven approach for targeted marketing in enterprise information system

Abstract

ABSTRACT In the rapidly evolving landscape of digital marketing, leveraging data analytics within Enterprise Information Systems (EIS) has become crucial for businesses aiming to understand and engage their customers more effectively. This study presents a comprehensive analysis of data-driven marketing strategies, emphasising the critical role of diverse data sources in developing targeted, EIS-specific campaigns. Central to our investigation is a comparative analysis of various machine learning algorithms, including Random Forest, CART, Support Vector Machine, Linear Discriminant Analysis, Logistic Regression, K-Nearest Neighbours, and Naïve Bayes. Our selection and evaluation of these models are grounded in their ability to address the complex dynamics of customer behaviour and marketing data, demonstrating the superior efficacy of Random Forest and CART in this context.