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{196378,
        author = {MEGHARAJ UPADHYE and Arundhati Hiremath and Smita Desai and Bharati A},
        title = {AI-Based Customer Intelligence For Smarter Retail Decision Making Using Unsupervised Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {3725-3734},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196378},
        abstract = {Understanding customer behavior is a critical challenge in modern retail, where traditional demographic-based segmentation methods such as grouping customers by age or gender fail to capture actual purchasing patterns and spending tendencies. This study proposes an unsupervised machine learning approach to customer segmentation that enables data-driven retail decision-making through behavioral analysis.
The proposed system applies the K-Means clustering algorithm to the Mall Customers dataset, segmenting customers based on two key behavioral indicators: annual income and spending score. The optimal number of clusters was determined using the Elbow Method, evaluating Within-Cluster Sum of Squares (WCSS) across values of k from 2 to 10. To ensure accessibility for non-technical users, an interactive dashboard was developed using Python and Streamlit, enabling retail managers to explore customer segments visually without requiring programming expertise.
Experimental results identified five distinct customer segments, including high-income low-spending consumers, low-income high-spending consumers, and balanced mid-range spenders. These segments provide actionable insights for personalized marketing strategies, inventory planning, and customer retention initiatives. The study demonstrates that open-source machine learning tools combined with interactive visualization can effectively bridge the gap between complex analytical methods and practical retail applications.},
        keywords = {Customer Segmentation, K-Means Clustering, Unsupervised Learning, Retail Analytics, Machine Learning, Data Visualization},
        month = {April},
        }