Mobile Edge Networks with Machine Learning for Cosmetics Brand Positioning and Value Assessment

Abstract

To ensure that products gain wider consumer recognition and to build brand value, the cosmetics industry should focus on researching and developing better products while shaping a more favorable brand positioning to enhance its competitiveness. As intelligent mobile edge computing (MEC) continues to be integrated with Internet of Things (IoT) technologies, concerns arise over its capacity to handle the computational complexity of Machine Learning (ML) methodologies, particularly for large-scale IoT data monitoring. Despite these challenges, MEC provides many benefits, including real-time data processing and enhanced customer engagement. This paper aims to provide an Intelligent Dynamic Cosmetics Brand Positioning using Internet of Things-based Mobile Edge Computing (IDBP-IoT-MEC). One of the core methodologies used in this model is Support Vector Machines (SVMs), a powerful ML technique for classification and regression tasks. SVMs, known for their ability to handle high-dimensional data, will be utilized to assess and classify consumer preferences, brand perception, and market trends based on large-scale IoT data collected from edge devices. By applying SVMs, the IDBP-IoT-MEC framework can efficiently monitor and predict customer behavior, enabling more dynamic and accurate brand positioning in a highly competitive market. Moreover, validated assessment methodologies play a critical role in evaluating the efficacy of cosmetic products, promoting both innovation and competition. SVM-based evaluation models are a suitable and efficient tool for assessing the benefits of new cosmetics, providing insights into consumer needs and market trends. These insights can help cosmetic companies properly communicate product benefits to consumers while encouraging research and development of improved cosmetic formulations.