What is it about?
In the digitalization of the present world, customer-based E-services have made a lot of progress because of the fusion of the E-commerce sector with the machine learning paradigm. It presents an appropriate, flexible, and easy-to-use environment for the customers to purchase the products and give them a variety of products through the Internet. Today's industrial scenario moves toward the client-centric market. So, this market requires the effective partitioning of customers using influential effective elements. This paper presents a detailed study of customer behavioral and segmentation models for E-satisfaction using K-Means, modified K-means, and other variations of K-based clustering techniques.
Featured Image
Photo by Robert Bye on Unsplash
Why is it important?
This paper provides a comparison of the statistical and analytical results of various existing models along with the consideration of their data attributes and effective elements. Further, it provides suggestions and extensions to improve their results in the E-market. It also signifies the need for a K-prototype algorithm. Therefore, such a review provides an analysis of the E-Satisfaction, and of the behavior and loyalty of the customers in the ML-based paradigm.
Perspectives
This paper provided a detailed and systematic study of existing customer behavior analysis and segmentation systems for E-satisfaction. Many research works were compared with each other based on the key criteria and their performance was distinguished from each other. These criteria included the concerned problems, products and services considered, and performance results. They were discriminated against based on the effective elements. Subsequently, their gaps, limitations, and critical issues were identified. This paper also illustrated their extension areas in terms of future suggestions and requirements. Further, the analytical results were graphically shown to depict the % contribution in using different types of datasets and in using the K-Means, variants, and other clustering algorithms.
Shalini Puri
Manipal University
Read the Original
This page is a summary of: Customer segmentation and behavioral systems through influential effective elements: An E-satisfaction analysis using machine learning, January 2023, American Institute of Physics,
DOI: 10.1063/5.0154287.
You can read the full text:
Resources
Contributors
The following have contributed to this page
