SkinMatch: AI-Enhanced Product Recommender

SkinMatch: AI-Enhanced Product Recommender

Yogita Chavan, Prajwal Hunasikatti, Pratiksha Hunasikatti, Keshav Margi, Komal Mewara

Department of Computer Engineering

New Horizon Institute of Technology and Management Thane, India

Abstract— Skin conditions affect millions worldwide, making personalized skincare recommendations essential for effective treatment and care. This work introduces SkinMatch, an AI- enhanced product recommender that leverages EfficientNet, a state-of-the-art Convolutional Neural Network (CNN), to classify skin conditions accurately. The system employs TensorFlow 2.x or PyTorch for deep learning, OpenCV for image processing, and a Flask-based web framework for seamless user interaction. By integrating computer vision with a robust recommendation system, SkinMatch analyzes user-uploaded facial images, detects skin conditions, and suggests suitable skincare products such as moisturizers, primers, and serums. SkinMatch aims to bridge the gap between AI-driven dermatological analysis and real-world skincare solutions, offering a scalable and user-friendly platform.

Keywords—Skin condition classification, EfficientNet, CNN, AI- powered skincare, product recommendation, deep learning, Flask, OpenCV, TensorFlow, PyTorch.