Trained a machine learning model to perform sentiment analysis on student reviews, automating the classification of feedback to help Queen's University improve teaching quality and student satisfaction.

This data analysis project utilizes a machine learning model to identify and predict the key drivers of customer satisfaction at a restaurant, with a goal of increasing revenue and improving the customer experience.

Leverages K-Means clustering to segment hotel guests based on their booking behaviors, with the goal of creating data-driven marketing strategies to increase revenue and customer satisfaction.

Developed a machine learning pipeline to predict insurance fraud by preparing and analyzing claims data, then training a Random Forest model that achieved a 70% greater fraud detection rate than random sampling, resulting in potential annual savings of $5.9 million.