Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{196927,
        author = {Samtham Hari Priya Devi and Polisetty Durga Harshitha and Chinthapatla Siddhartha and Lakkamaraju Sai Sohith Varma and K.V.D.Kiran},
        title = {Consumer Behavior Segmentation using Variational Autoencoder on RFM Data},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {6148-6154},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196927},
        abstract = {Consumer Behavior analysis plays an essential part in modern e-commerce systems as it ensures the preservation of the target audience and the right marketing campaigns. At present, customer segments are created on the basis of the RFM model, which consists of Recency, Frequency, and Monetary value, but it does not take into account the complexities of consumer behavior. The purpose of this paper is to propose a technique for consumer segmentation via the application of the Variational Autoencoder algorithm to build RFM embedding space. First, it is supposed to train the VAE algorithm for obtaining embeddings based on RFM values. For embedding generation, one may project consumer RFM values on the manifold latent space. Besides, the reconstruction error resulting from the training process can be utilized as a criterion for measuring embedding quality. Clustering can be applied for classifying consumers according to their behavior into Loyal, Potential, Fresh, and At-Risk segments. Finally, a dashboard is created to perform clustering through visual analytics. As follows from the results of the experiment, the technique proposed for consumer segmentation based on the generation of embeddings via RFM proved its efficiency.},
        keywords = {Consumer Behavior Analytics, Deep Learning, E-Commerce, RFM Model, Variational Autoencoder, Customer Segmentation.},
        month = {April},
        }