An Intelligent Customer Analytics Framework Using RFM Segmentation and Hybrid Recommendation Systems
Nisha Pal, Anupma, Kajal Chaudhary, Sanjay Kumar
Galgotias College of Engineering & Technology
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
Personalized recommendation systems and customer segmentation contribute significantly to enriching user experience and optimizing marketing strategies in the retail and ecommerce sectors.Traditional recommendation approaches usually suffer from issues of limited personalization and scalability.This paper presents an integrated system that combines customer segmentation based on Recency-Frequency-Monetary (RFM) analysis with customized product recommendations using content-based, collaborative, and hybrid filtering techniques.Customers are divided into four classes-Loyal Customers, Potential Loyalists, New Customers and At-Risk Customers by the implementation of K-Means clustering.Principal Component Analysis (PCA) is utilized to visualize multidimensional data and analyze the dispersion of customer behaviors across clusters.Personalized recommendations are produced by examining both product features and customer interactions, whereas the hybrid model combines these analyses to gain better accuracy and relevance.The system proposed has been implemented as an interactive Streamlit dashboard that allows real-time analysis, visualization and generation of recommendations.Empirical analysis shows that the hybrid model consistently generates more contextually appropriate recommendations than single filtering methods, demonstrating real-world usefulness for data-driven, customer-centric business approaches.
逐年被引趋势
暂无年度引用数据
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
经济 / 管理Customer churn and segmentation
Recommender Systems and Techniques · Data Mining and Machine Learning Applications