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{207512,
        author = {Nakka Janakibai},
        title = {GAN‑Based Synthetic Data Augmentation And SVM Driven Customer Segmentation In Retail BI Systems},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {3},
        pages = {1371-1376},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207512},
        abstract = {The integration of synthetic data generation and machine learning classification offers a transformer approach to retail analytics and decision intelligence. This study Proposes a framework that leverages Generative Adversarial Networks (GANs) to-produce realistic synthetic retail transaction datasets, addressing challenges of limited historical data and privacy concerns. The generated data is subsequently classified using Support Vector Machines (SVM), enabling segmentation of customers, prediction of-product demand categories, and identification of purchasing patterns. These classified insights are embedded into interactive Business Intelligence (BI) dashboards, providing stakeholders with actionable visualizations such as sales heat maps, customer segmentation cards, and trend forecasts. The proposed system demonstrates how Gan driven synthetic data, combined with SVM classification, can enhance scalability,preserve confidentiality, and deliver predictive intelligence for retail decision-making. By bridging advanced data science techniques with BI visualization, this framework empowers organizations to simulate diverse market scenarios, anticipate consumer behavior, and optimize strategic planning in data-constrained environments.The rapid expansion of AI and ML applications has heightened the demand for large, diverse, and high-quality datasets. The purpose of the Synthetic Data volume generator is overcoming the data scarcity or protecting sensitive information. The methods that are used in synthetic data volume generators are Generative Adversarial network(GAN) and Variational Auto encoders. A Variational Auto encoder is a machine learning model that can generate new data based on the data its trained on. Variational Auto encoders are used in many applications like image generation, text generation and data denoising.},
        keywords = {GAN, SVM and BI-Dashboard},
        month = {August},
        }