Skincare Recommendation System Based on Facial Skin Type with Real-Time Weather Integration

Skin conditions can be significantly affected by unpredictable weather changes, creating the need for a solution that can provide personalized skincare product recommendations. This study presents the development of an AI-based skincare recommendation system that integrates skin type classification using Convolutional Neural Networks (CNN) with real-time weather data via the OpenWeatherMap API. The system consists of three main components: a ResNet50-based Skin Analyzer, a Weather Analyzer using the Decision Tree algorithm, and a Product Recommendation module. The image dataset is sourced from two Kaggle datasets: "Dry, Oily, and Normal Skin Types" and "Acne Dataset." The total dataset consists of 2,885 images, divided into four classes: Acne (549 images), Dry (652 images), Normal (884 images), and Oily (800 images). The dataset exhibits diversity in skin types, allowing for a more valid evaluation of the CNN model. The training and testing process involved splitting the data into training and testing sets, with augmentation applied to the training data to enhance the feature diversity across classes. Evaluation results show an average validation accuracy of 90.94% ± 0.60% with consistent performance. This system aids users in identifying their skin type and suggests appropriate skincare products based on current weather conditions. It is expected to contribute to the advancement of AI-driven personalization in the skincare industry.