Open Access

ARTICLE

Privacy-Preserving Gender-Based Customer Behavior Analytics in Retail Spaces Using Computer Vision

Ginanjar Suwasono Adi¹, Samsul Huda^2,*, Griffani Megiyanto Rahmatullah³, Dodit Suprianto¹, Dinda Qurrota Aini Al-Sefy³, Ivon Sandya Sari Putri⁴, Lalu Tri Wijaya Nata Kusuma⁵

1 Artificial Intelligence of Things Research Group, Department of Electrical Engineering, Politeknik Negeri Malang, Malang, 65141, Indonesia
2 Interdisciplinary Education and Research Field, Okayama University, Okayama, 700-8530, Japan
3 Department of Electrical Engineering, Politeknik Negeri Bandung, Bandung, 40559, Indonesia
4 Department of Business Administration, Politeknik Negeri Bandung, Bandung, 40559, Indonesia
5 Department of Industrial Engineering, Faculty of Engineering, Universitas Brawijaya, Malang, 65145, Indonesia

* Corresponding Author: Samsul Huda. Email:

(This article belongs to the Special Issue: Towards Privacy-preserving, Secure and Trustworthy AI-enabled Systems)

Computers, Materials & Continua 2026, 86(1), 1-23. https://doi.org/10.32604/cmc.2025.068619

Received 02 June 2025; Accepted 17 September 2025; Issue published 10 November 2025

Abstract

In the competitive retail industry of the digital era, data-driven insights into gender-specific customer behavior are essential. They support the optimization of store performance, layout design, product placement, and targeted marketing. However, existing computer vision solutions often rely on facial recognition to gather such insights, raising significant privacy and ethical concerns. To address these issues, this paper presents a privacy-preserving customer analytics system through two key strategies. First, we deploy a deep learning framework using YOLOv9s, trained on the RCA-TVGender dataset. Cameras are positioned perpendicular to observation areas to reduce facial visibility while maintaining accurate gender classification. Second, we apply AES-128 encryption to customer position data, ensuring secure access and regulatory compliance. Our system achieved overall performance, with 81.5% mAP@50, 77.7% precision, and 75.7% recall. Moreover, a 90-min observational study confirmed the system’s ability to generate privacy-protected heatmaps revealing distinct behavioral patterns between male and female customers. For instance, women spent more time in certain areas and showed interest in different products. These results confirm the system’s effectiveness in enabling personalized layout and marketing strategies without compromising privacy.

---

Keywords

---