This project aims to build a Personalized Fashion Recommendation System using the H&M Personalized Fashion Recommendations dataset. The primary goal is to segment customers based on recency, frequency, and monetary, and recommend relevant products to customers based on their past interactions. The dataset, sourced from Kaggle, includes large transaction files and skewed distribution that pose significant challenges in terms of processing and analysis. The outcome is being able to identify customer lifetime value, design an effective CRM strategy, and utilize product recommendation to re-engage with the customers.