The Impact of Artificial Intelligence on Predictive Customer Behaviour Analytics in E-commerce: A Comparative Study of Traditional and AI-driven Models

• Author(s): Nigel Nkomo ; Munashe Naphtali Mupa
• Paper ID: 1706548
• Page: 432-452
• Published Date: 21-11-2024
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 8 Issue 5 November-2024

Abstract

This comparative article explores the impact of artificial intelligence (AI) on predictive customer behaviour analytics in the e-commerce sector, evaluating AI-driven models against traditional approaches. Traditional models, including logistic regression, decision trees, and clustering methods, have long been employed to predict customer behaviours, such as purchasing decisions and churn, based on historical data. However, these models face significant limitations regarding scalability, accuracy, and the ability to process vast and complex datasets. In contrast, AI-driven models—particularly those utilizing machine learning (ML), deep learning (DL), and natural language processing (NLP)—demonstrate superior performance by processing large volumes of data, identifying non-linear patterns, and delivering real-time predictions. AI’s enhanced capabilities enable e-commerce platforms to offer hyper-personalized customer experiences, improve marketing strategies, and optimize operational efficiency. The article further explores the integration of AI with other emerging technologies, such as the Internet of Things (IoT) and blockchain, enhancing predictive analytics by ensuring data integrity and real-time processing. However, challenges persist, especially concerning the interpretability of AI models, often referred to as "black-box" systems, which limit transparency and trust in high-stakes sectors. Explainable AI (XAI) is identified as a crucial development for improving model transparency and accountability. Additionally, ethical concerns related to data privacy, bias, and fairness in AI models are discussed, underscoring the need for robust regulatory frameworks. Hence, the article concludes that while AI-driven models significantly outperform traditional methods in predictive analytics, addressing challenges in interpretability, bias, and ethical concerns will be critical for their broader adoption and trustworthiness in the e-commerce sector. Future research is recommended to enhance AI transparency, fairness, and integration with emerging technologies.

Citations

IRE Journals:
Nigel Nkomo , Munashe Naphtali Mupa "The Impact of Artificial Intelligence on Predictive Customer Behaviour Analytics in E-commerce: A Comparative Study of Traditional and AI-driven Models" Iconic Research And Engineering Journals Volume 8 Issue 5 2024 Page 432-452

IEEE:
Nigel Nkomo , Munashe Naphtali Mupa "The Impact of Artificial Intelligence on Predictive Customer Behaviour Analytics in E-commerce: A Comparative Study of Traditional and AI-driven Models" Iconic Research And Engineering Journals, 8(5)