Impact of AI-driven personalization on consumer purchase intent in e-commerce brands: A case study approach for final-year marketing students

Project Abstract

This study investigates how AI-driven personalization influences consumer purchase intent within e-commerce brands through a case study approach focusing on final-year marketing students as researchers and participants. Grounded in theories of consumer behavior, personalization, and technology acceptance, the research examines the mechanisms by which personalized recommender systems, dynamic content, and individualized messaging shape perceived relevance, trust, perceived control, and ultimately willingness to purchase. A mixed-methods design is employed across three e-commerce brands operating in distinct segments (fashion, electronics, and beauty) to ensure transferability of findings. Quantitative data are collected via a structured survey administered to 600 customers exposed to AI-personalized experiences and 300 customers who encountered generic, non-personalized interfaces, enabling causal inference through propensity score matching and multi-group structural equation modeling. The qualitative strand comprises 30 in-depth interviews with customers, 12 with brand marketing managers, and 6 with data scientists to capture nuanced explanations for observed behavioral differences and implementation challenges. Data collection occurs over six months, with longitudinal tracking of purchase intent, click-through behavior, basket size, and repeat visitation, alongside measurements of moderating variables such as demographic profiles, digital literacy, privacy concerns, trust in automated systems, and perceived privacy risk. The analysis seeks to identify which personalization modalities—product recommendations, personalized pricing cues, adaptive content, and behavioral-triggered messages—most strongly influence purchase intent and under what situational conditions. The study also investigates potential behavioral backlash effects, including perceived manipulation and decision fatigue, and examines how explainability and opt-out controls impact consumer attitudes and intentions. Findings are expected to reveal a differential impact of personalization intensity by product category, user context, and prior brand familiarity, with high relevance and timely relevance cues showing stronger conversion effects. The research contributes to theory by integrating AI personalization with purchase intention frameworks, privacy calculus, and trust-commitment models, and to practice by offering actionable guidelines for marketers on optimal personalization design, governance, and transparency practices to balance revenue growth with consumer autonomy and ethical considerations. Methodological rigor is maintained through triangulation, reflexivity logs, and pre-registered analysis plans, while ensuring ethical compliance with consent, anonymization, and data protection standards. The study also assesses the role of organizational capabilities—data quality, algorithmic fairness, and cross-functional collaboration—in enabling effective personalization strategies. Implications for final-year marketing students include a structured, scalable case study methodology, skill-building in experimental design, data interpretation, and the critical evaluation of AI-enabled consumer interventions. Policy implications address consumer privacy, algorithmic accountability, and best practices for transparent disclosure of personalization techniques. By unpacking the pathways from AI-driven personalization to purchase intent, the research provides a nuanced understanding of how intelligent marketing ecosystems can influence consumer decisions in e-commerce while maintaining trust and ethical integrity.

Project Overview

What This Project Is About

---

A straightforward examination of how personalized features powered by artificial intelligence influence whether people intend to buy from online stores. The project uses a real-world case study approach to show how brands tailor product recommendations, emails, and website experiences to individual shoppers and how these efforts affect purchase intent.

---

---

The Problem It Addresses

---

Many e-commerce sites rely on generic marketing that may not connect with individual shoppers. This project investigates whether AI-driven personalization actually boosts a shopper’s interest in buying, and identifies which personalized elements are most effective. It helps students understand the practical value of personalization in online retail.

---

---

Objectives of the Project

---

1. Explain what AI-driven personalization means in simple terms.
2. Describe how personalization can affect a shopper’s intent to purchase.
3. Analyze a real e-commerce case to identify effective personalization strategies.
4. Assess potential challenges and ethical considerations in using personalized data.
5. Provide practical takeaways for marketers aiming to improve purchase intent.

---

---

What You Will Do Step by Step

---

1) Review basic concepts of AI-driven personalization in e-commerce. 2) Select a real brand’s case with available data or publicly shared examples. 3) Map personalized elements used (recommendations, emails, banners). 4) Explain how these elements are expected to influence purchase intent. 5) Collect and summarize user responses or case data. 6) Analyze gaps and limitations in the data. 7) Discuss practical implications for marketers. 8) Present concise recommendations.

---

---

---

---

Expected Outcome

Clear understanding of which personalized features most strongly influence purchase intent, plus actionable guidance for marketers on implementing ethical, effective personalization in online shopping.