Product Recommender System

Date: Jul 2023 - Mar 2024

Roles: Data Scientist

This project was completed while I was a consultant at Melio AI, and some of the project details have been obfuscated.

Overview

Designed and tested a product recommender system to enhance marketing campaigns by providing personalised product suggestions to users.

My Responsibilities

• Made decisions around model architectures and implementation for recommender systems.
• Created custom recommender system that took sequence of user-product interactions into account.
• Compared different models and tools to find optimal solutions.
• Estimated ROI to assess business viability based on model performance.

Outcomes/Impact

• Improved customer personalization and product take-up compared to existing strategy (in offline tests).

Tools Used

• Python
• Docker
• AWS
• AWS SageMaker
• AWS Personalize
• TensorFlow
• Scikit-Learn