Carnegie Mellon University

LISI: Implementing a Newsletter Recommendation System: How Leimberg Services Inc. Can Improve Customer Satisfaction

Capstone Team: Cyndia Chen, Olivia Dion, Jackie Sun, Haowei Song, Yifei Wang

This paper explores the implementation of a newsletter recommendation system for Leimberg Services Inc. (LISI) to enhance customer satisfaction. The research leverages machine learning algorithms and data analysis to segment subscribers and predict their newsletter interests. By collecting demographic information and consumption records, along with newsletter content, the study identifies clusters of subscribers and matches them with relevant newsletters based on keyword similarity. The findings provide valuable insights for LISI to personalize email marketing campaigns, improve customer segmentation, and conduct A/B testing for optimization. The proposed strategies encompass recommendation systems, customer segmentation, and A/B testing, which can contribute to increased subscriber engagement, retention, and revenue. Additionally, suggestions are given for future improvements, including adjusting the registration system, providing clearer categorization options, and establishing a comprehensive database with interactive data collection. These recommendations aim to enhance personalization, improve user experience, and enable data-driven decision-making to optimize LISI's service and content over time.

Capstone Presentation