OPTIMIZATION OF FASHION RETAIL CUSTOMER DATA MANAGEMENT THROUGH EXPLORATORY DATA ANALYSIS AND RECENCY, FREQUENCY, MONETARY

Abstract

This study was conducted to analyze revenue patterns, product segmentation, and customer retention in the H&M retail business using Kaggle competition data "H&M Personalized Fashion Recommendations." The urgency of this study lies in the need to understand revenue fluctuations and customer behavior in order to optimize business strategies. The data used includes transactions, articles, and customer profiles from 2018 to 2020. The analysis methods applied include exploratory data analysis (EDA) analysis and customer segmentation using the RFM (recency, frequency, and monetary) model to identify customer groups based on purchasing behavior. The results of the study show that the highest revenue occurs in the middle of the year, with a sharp decline in growth in mid-2018. Low-recency customers contribute more to revenue, while product segmentation shows the need for stock adjustments, especially for baby/children and divided products. This study successfully identified key factors that influence revenue and customer retention and provided strategic recommendations for inventory improvement and market segmentation. These results are important for H&M to improve operational efficiency and improve marketing strategies in the future.