AI-Driven Personalization Strategies to Enhance Customer Engagement in Ecommerce

Thesis Abstract

The rapid growth of ecommerce platforms and the increasing competition within the digital marketplace have necessitated the adoption of advanced technologies to personalize customer experiences and foster sustained engagement. Despite significant investments in digital marketing strategies, many ecommerce enterprises encounter challenges in effectively tailoring product recommendations and content to individual consumers, leading to suboptimal shopping experiences and reduced customer loyalty. This study aims to develop a comprehensive understanding of AI-driven personalization strategies and their impact on customer engagement within ecommerce contexts. The specific objectives include (1) to identify the key AI-enabled personalization techniques utilized by ecommerce platforms; (2) to evaluate the effectiveness of these strategies in enhancing customer engagement metrics such as time spent, conversion rates, and repeat purchases; (3) to examine the moderating effects of consumer demographics and behavior on personalization success; and (4) to propose an integrated conceptual framework for AI-based personalization that optimizes customer engagement outcomes. Employing a mixed-methods research design, the study combines quantitative data analysis with qualitative insights to provide a holistic view of personalization strategies. The quantitative component involved a survey administered to 430 active ecommerce customers across multiple retail sectors, selected through stratified random sampling to ensure demographic diversity. Data collection instruments included a structured questionnaire measuring perceptions of personalization, engagement levels, and satisfaction, validated through Cronbach's alpha coefficients exceeding 0.85. In addition, transactional data from partner ecommerce platforms—comprising over 1.2 million user interactions over twelve months—were analyzed to assess behavioral responses to personalization techniques. Qualitative data were gathered through semi-structured interviews with 15 ecommerce marketing managers, exploring strategic implementation challenges and perceived effectiveness. The data were analyzed using multiple statistical techniques, including multiple regression analysis to determine the relationship between personalization strategies and engagement metrics, and moderating effect analysis via PROCESS macro to identify the influence of demographic variables. Thematic analysis was applied to interview transcripts to identify recurring themes related to strategy deployment and success factors. Structural Equation Modeling (SEM) was used to test the proposed conceptual framework, assessing the interrelationships among AI-driven personalization practices, customer perceptions, and engagement outcomes. Preliminary findings suggest that advanced AI techniques such as machine learning-based product recommendations and natural language processing-driven chatbots significantly enhance key engagement indicators. Personalization accuracy was found to be positively correlated with increased session duration, higher conversion rates, and greater customer retention. Furthermore, consumer characteristics—such as age, prior familiarity with AI technology, and purchase history—moderated the effectiveness of personalization, indicating the need for tailored approaches across different demographic segments. The qualitative insights underscored strategic alignment as critical to successful deployment of AI strategies, with barriers including data privacy concerns and technical complexity. This research contributes to the scholarly understanding of AI-driven personalization in ecommerce by empirically validating a conceptual framework that links technological practices to customer engagement outcomes within a mediated model incorporating consumer diversity factors. It advances existing literature by integrating multiple data sources and analytical techniques to present a nuanced view of personalization efficacy in real-world settings. Based on these findings, the study recommends that ecommerce firms invest in sophisticated AI tools capable of dynamic learning and contextual adaptation to improve personalization accuracy. The integration of demographic insights into personalization algorithms is advised to address diverse customer needs effectively. Additionally, firms should develop comprehensive data governance policies to mitigate privacy concerns and build customer trust. Future research should explore longitudinal effects of AI personalization on customer lifetime value and investigate emerging AI modalities such as emotion recognition and virtual assistants. Ultimately, this study offers actionable insights and a validated framework to guide ecommerce practitioners and scholars toward leveraging AI-driven personalization for enhanced customer engagement and competitive advantage.