Design and evaluate a personalized AI-driven marketing chatbot for e-commerce engagement

Thesis Abstract

In the rapidly evolving landscape of e-commerce, personalized customer engagement has emerged as a critical determinant of competitive advantage, yet many platforms struggle to implement scalable, effective, and customer-centric interaction strategies. This study addresses the challenge of enhancing e-commerce engagement through the integration of intelligent, tailored communication tools by designing and evaluating a personalized AI-driven marketing chatbot. The primary aim is to develop a chatbot that leverages artificial intelligence and machine learning to deliver personalized product recommendations, promotional messages, and customer support, thereby improving user engagement, satisfaction, and conversion rates. The specific objectives are to (1) examine existing AI chatbot frameworks and personalization techniques within e-commerce, (2) design a prototype chatbot employing advanced natural language processing (NLP) and machine learning algorithms, (3) evaluate the chatbot's effectiveness in fostering consumer engagement and purchase intention, and (4) analyze user perceptions and satisfaction with the AI-driven system. Methodologically, the research adopts a mixed-methods approach comprising quantitative and qualitative elements. The quantitative component involves a quasi-experimental design with a sample of 300 active users of an online retail platform, selected through stratified random sampling to ensure representativeness across demographic segments. Data collection instruments include pre- and post-interaction surveys measuring engagement metrics, satisfaction, and purchase intention, complemented by system logs capturing interaction data. Qualitative data are collected through semi-structured interviews with 15 participants to explore user experiences and perceptions in depth. The chatbot prototype is developed based on the Theory of Planned Behavior and the Technology Acceptance Model (TAM), guiding the design of personalization strategies and user interface features. Data analysis employs descriptive statistics, paired-sample t-tests, and multiple regression analysis to evaluate the chatbot's impact on engagement and conversion rates. Thematic analysis is utilized to interpret qualitative interview data, providing insights into user perceptions, barriers, and facilitators of chatbot acceptance. A detailed analytical framework is established for assessing the system’s performance, including accuracy of personalization, response relevance, and user satisfaction levels. Expected findings anticipate that the personalized AI chatbot will significantly increase user engagement, as evidenced by higher time-on-site, repeat visits, and purchase rates, compared to baseline data. The study also expects to find positive correlations between perceived system usability, perceived usefulness, and overall customer satisfaction. Insights from qualitative interviews are expected to reveal enhancement opportunities and factors influencing trust and system adoption. These outcomes will demonstrate the efficacy of AI-driven personalization strategies in e-commerce, providing empirical evidence for their integration into digital marketing practices. The study's contribution to knowledge lies in providing a comprehensive framework for designing, implementing, and evaluating personalized AI chatbots tailored specifically for e-commerce environments. It extends existing literature by bridging the gap between theoretical models of technology acceptance and practical chatbot applications, offering a replicable model that combines cutting-edge AI techniques with marketing strategy. The research also offers empirical validation of the relationship between personalization, user engagement, and purchase behavior, informing future development of intelligent customer interaction tools. In conclusion, the study affirms that AI-powered personalized chatbots can substantially enhance e-commerce engagement and customer satisfaction. Based on the findings, it is recommended that online retailers prioritize the integration of advanced NLP and machine learning algorithms in their customer service frameworks to foster deeper engagement. Further research is suggested to explore long-term impacts, scalability in diverse market contexts, and integration with other AI-driven marketing tools, such as personalized advertising and omnichannel customer journeys. This research underscores the importance of technological innovation in shaping the future of customer-centric e-commerce marketing.