AIDA-Based Customer Segmentation With User Journey Analysis for Wi-Fi Advertising System

Customer segmentation is an important aspect in aiding businesses to comprehensively understand their customer base and tailor their marketing strategies for optimal effectiveness. Traditional approaches to segmentation have predominantly concentrated on demographic factors and observable characteristics. However, these approaches have limitations that prevent them from capturing the intricate user journeys of each identified segment. Hence, this paper proposes an approach to customer segmentation using clustering algorithms, specifically the K-Means, BIRCH, and Gaussian Mixture Model on the dataset derived from the Wi-Fi advertising system, with a focus on tracking the user progression through the stages of the AIDA (Attention, Interest, Desire, Action) Model. This paper not only presents an AIDA-based metric designed for Wi-Fi advertising data, it also strives to measure the different stages in the user journey analysis. Through the combination of the AIDA Model and the clustering algorithms, the main objective is to gain a nuanced understanding of the distinct stages characterizing the user journey within each identified segment. This approach further incorporates a dynamic-characteristics range table to delineate the weak and strongly engaged behavioral traits, thereby demonstrating the efficacy of combining the AIDA Model with the clustering algorithms in unraveling nuanced insights into customer behavior across diverse stages of the user journey for each segmented group. Based on the detailed AIDA levels of each user segment, it suggests actionable insights for businesses to enhance marketing strategies by identifying which stages to emphasize, ultimately leading to improved campaign effectiveness and user satisfaction.