Consumer segmentation and profiling using demographic data and spending habits obtained through daily mobile conversations.

Abstract

Knowledge of customer behaviour helps organizations to continuously re-evaluate their strategies with the consumers and plan to improve and expand their application of the most effective strategies. The Kenyan consumer remains dynamic and the market is increasingly become transformational, characterised by high population growth, a youthful demographic, healthy urbanization, an emerging optimistic consumer class, albeit with unpredictable expenditure patterns. In addition to understanding demographic habits and product preferences, comprehensively factoring in consumer spending habits, their relationship to marketing reception and brand reception, and how they morph with time is crucial. Customer segmentation and profiling has become an indispensable tool for organisations to understand all these. The process is based on both internal data on expenditure, augmented by other research data. The consumer, however, does not spend in isolation. Every purchase they make affects another. Using expenditure data collected through daily mobile conversations with consumers in Kenya, this study sought to compare various clustering algorithms and establish one that best segments consumers, and subsequently providing profiles that provide a basis for marketing and brand strategy based on existing demographic data – age, gender, region and primary income source. K-Means, Hierarchical and Partitioning around Medoids (PAM) clustering algorithms were compared using internal and stability validation tests. Internal validation consists of three measures that compare the compactness, connectedness and separation of the cluster partitions through the Connectivity, Dunn index and Silhouette measures. Hierarchical clustering with four clusters had the best Connectivity (0.847) and Silhouette width (0.924) measures. Stability validation compares the results by removing a column, one at a time. Average Proportion of Non-overlap (APN), Average Distance (AD), Average Distance Between Means (AND) and Figure of Merit (FOM) were used to compare the algorithms. Again, Hierarchical clustering with four clusters was found to partition the data best. A rank aggregation of the two measures was not different. A four cluster Hierarchical fit performed best in four out of seven measures. The algorithm was fit into the data using an agglomerative approach and the four clusters profiled based on the available demographic characteristics. The study forms a basis for the use of additional profile descriptors once available to provide a firmer understanding of the customer segments built on expenditure data in Kenya. Thereafter, classification into a specific homogenous segment for marketing and brand targeting will be possible, given the consumers demographic characteristics.