Personalized Satisfaction Prediction and Mismatch Detection Using Machine
Authors
Kadouri, Bouchra
Issue Date
2025.16.12
Degree
HDip in Data Analytics
Publisher
Dublin Business School
Rights holder
Rights
Open Access
Abstract
This project focuses on improving customer satisfaction by using machine learning to predict how likely a customer is to be happy with a service. It also helps identify when there’s a mismatch between what the customer actually felt and what the system predicted. By analyzing past feedback and satisfaction data, the model can make accurate predictions. We measured its performance using common evaluation methods like precision, recall, and ROC curves. To make the results easy to understand, we used Power BI to create clear visualizations. This approach can help companies offer more personalized services, fix issues early, and keep their customers happier.