Unveiling IoT Customer Behaviour: Segmentation and Insights for Enhanced IoT-CRM Strategies: A Real Case Study

Area of Science:

• Consumer Behavior Analysis
• Internet of Things (IoT) Ecosystems
• Data Mining and Machine Learning Applications

Background:

• Customer-centricity is crucial for organizational growth in competitive markets.
• The Internet of Things (IoT) presents unique challenges and opportunities for understanding consumer preferences.
• Existing research often lacks a segmented approach to IoT customer behavior.

Purpose of the Study:

• To understand customer preferences and segmentation within the IoT context.
• To identify key factors influencing customer satisfaction and purchase decisions for IoT devices.
• To provide actionable insights for enhancing customer retention and loyalty in the IoT ecosystem.

Main Methods:

• A two-part modeling approach was employed, starting with Self-Organizing Map (SOM) for customer segmentation.
• Classification and Regression Tree (CART) technique was used to analyze factors influencing IoT purchase decisions and satisfaction.
• Surveys and questionnaires were distributed to 207 IoT users, analyzed using statistical methods and IoT-CRM tools.

Main Results:

• Three distinct IoT customer clusters were identified using SOM, with one cluster showing higher adoption and usage propensity.
• Key factors influencing IoT device purchase decisions and satisfaction were prioritized using CART analysis.
• The study provides visualisations essential for understanding the dynamics of the IoT customer landscape.

Conclusions:

• Customer segmentation and understanding key satisfaction drivers are vital for IoT businesses.
• Logical marketing strategies, improved customer satisfaction, and loyalty are critical for customer retention in the IoT era.
• The findings offer significant contributions for optimizing IoT-Customer Relationship Management (IoT-CRM) strategies.