AI for delivering product recommendation in retail consumer categories

E-commerce has evolved rapidly in recent decades resulted from globalization and international trade. The demand of online shopping is increasing every day, which has opened business opportunities to attract more costumers locally and globally. However, achieving satisfactory user experience in online shopping remains challenging compared to in-person walk-in shopping. Currently, customers have to input static text and images, or use webcam. Engaging interaction and automatic products recommendation is missing. In this project, we use eyeglasses as a use case to demonstrate how an AI-driven recommendation system can be designed and implemented for retail consumer categories. We will integrate image processing, computer vision and machine learning techniques to address the current issues of poor product recommendations. We will also create a basic deployment interface, enabling the trained model to integrate easily into a production environment.

Faculty Supervisor:

Irene Cheng

Student:

Maryam Sedghi;Rui Jessie Wang

Partner:

Eyevious Style

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

University of Alberta