Customer Personality Analysis Using Machine Learning with Explainable AI

Predicting customer behavior has become essential for understanding preferences and guiding marketing decisions across various industries. Machine learning and explainable AI (XAI) enable advanced analysis of customer personality traits, facilitating precise segmentation and customized strategies. This study integrates feature engineering, explainability techniques, and state-of-the-art machine learning models to enhance customer personality analysis. Our findings demonstrate that clustering techniques like K-Means significantly improve customer segmentation, while explainability techniques such as SHAP and LIME provide deeper insights into feature importance. Unlike traditional methods, XAI enhances interpretability by offering transparent, actionable insights that marketers can leverage to optimize campaigns and improve customer engagement. Among the various machine learning models evaluated, XGBoost demonstrated the highest performance improvement when applying balancing techniques. Specifically, using Random Oversampling, XGBoost achieved the highest Fl score of 0.8680 compared to other balancing methods. Furthermore, experimental results reveal that incorporating XAI-driven insights leads to a measurable increase in prediction accuracy and segmentation efficiency. The implications of this research extend to decision-making processes in customer-focused organizations, marketing campaign optimization, and customer relationship management. By integrating machine learning, clustering algorithms, and XAI, this study establishes a strong foundation for future customer analysis strategies, paving the way for real-time segmentation and targeted marketing.