Assessment of consumer preferences in laptop purchases: A segmentation and classification study from a transformational marketing perspective

Abstract

In a dynamic business environment, consumer segmentation is vital for growth and development. This study proposes an integrated approach using machine learning for post-hoc segmentation based on the benefits sought by consumers from a transformational marketing perspective. The research uses Support Vector Machine (SVM) and Decision Tree Classification (DTC) algorithms to perform the initial classification and the K-means algorithm to segment consumers according to their preferences. The sample consisted of 1,000 participants. The results revealed groups of consumers with distinctive preference/behavior patterns, providing a detailed view of the potential consumer portfolio. Within the framework of transformational marketing, these findings allow for the design of strategies beyond simple product promotion, focusing on personalized experiences and targeted communications. Benefit-based segmentation identified four segments: the first highlighting economy and usability, the second focusing on performance, the third showing preferences in design, performance, and economy, and the fourth highlighting design and performance. The study demonstrates that both the SVM and DTC algorithms have high performance in consumer classification, providing a solid foundation for the practical application of these techniques. In summary, this integrated machine learning approach offers a detailed and practical view of consumer segmentation, opening opportunities for more effective marketing strategies.