Insegnamento a.a. 2025-2026

The course is organized around several modules, each combining concepts, methods, and applications in market research:

• Foundations of LLMs and Generative AI for Market Research

• Prompt Engineering and LLM Evaluation

• Text Data Pipelines for Market Research

• Embeddings and Retrieval for Insight Generation

• AI-Augmented Survey and Experiment Design

• Applications in Marketing & Strategy

• Ethics, Governance, and Societal Impact

Throughout the course, students will work on practical projects where they design and implement AI workflows for real or realistic market research problems, using Python notebooks and/or LLM APIs and tools.

and econometric analysis.

• Explain the main concepts behind large language models and generative AI relevant for market research (pre-training, prompting, embeddings, retrieval).

• Describe how LLMs can be integrated into market research workflows: data collection, cleaning, coding, analysis, and reporting.

• Understand the role of embeddings and vector similarity for clustering, retrieval, and segmentation.

• Identify appropriate evaluation criteria and methods for assessing LLM-based tools (reliability, validity, bias, robustness).

• Recognize key ethical, legal, and societal issues related to using AI in marketing and consumer research.

• Implement end-to-end text analysis pipelines using LLMs and Python (or similar tools) to extract insights from unstructured data.

• Design and test prompts for different research tasks (classification, extraction, summarization, ideation) and refine them based on empirical feedback.

• Build and evaluate simple RAG or embedding-based applications for tasks such as insight search, FAQ automation, or clustering customer feedback.

• Use LLMs to assist in designing surveys and experiments, and critically assess when such assistance is appropriate.

• Design, document, and present an AI-enabled market research project that answers a specific managerial/research question, clearly explaining the methodological choices and limitations.

• Lectures
• Practical Exercises
• Individual works / Assignments

• Practical Exercises
  • In-class exercises
• Individual works / Assignments
  • Project Work
  • Project Presentation

For each topic in the course, we will combine lecture with hands-on exercises. Students will have opportunity to work with data to practice in LLM knowledge and techniques.

• Participation: 20%

  • Engagement in class, contribution to discussions, completion of in-class exercises.

• Assignments and Project: 30%

  • A set of individual or group assignments throughout the course.

  • Evaluation based on technical correctness, clarity of documentation, and depth of insight.

• Final Exam: 50%

  • Written exam on both conceptual knowledge and applied skills developed in the course.

  • May include interpretation of code and outputs, design of AI workflows for specific research problems, and critical assessment of AI methods.

Attendance will be registered at the beginning of the sessions.
To obtain the attending student status, students must attend at least 75% of the lessons.

• Final Exam: 100%

  • Comprehensive written exam covering the entire syllabus, with a focus on understanding concepts, methods, and applications.

  • May require reading and interpreting code snippets and AI workflows, even without having done the in-class exercises

• Lecture slides and Jupyter notebooks prepared by the instructor.

• Selected academic papers, reports, and practitioner articles on AI and market research.

• Links and documentation for LLM / AI tools and APIs used in class.

All materials will be made available on the course e-learning platform (e.g., Blackboard), along with instructions for software setup and data access.