In recent years, advancements in artificial intelligence have opened new avenues in dermatological care, especially in automating skin condition detection and enhancing personalized skincare recommendations. This study presents a novel smart dermatology framework that integrates a Convolutional Neural Network (CNN)-based model for precise skin anomaly detection with an intelligent product recommendation system tailored to individual dermatological profiles. The proposed system leverages a curated dataset comprising 10,000 annotated dermatoscopic images across seven major skin conditions, including acne, eczema, psoriasis, and melanoma. Preprocessing techniques such as data augmentation, normalization, and adaptive resizing were applied to improve model generalizability across diverse skin tones and image conditions. A custom CNN architecture featuring three convolutional blocks, ReLU activations, max-pooling, and dense layers was employed, achieving a test accuracy of 91.6% and an F1-score of 0.89. Following successful classification, the system maps detected conditions to a dynamic skincare product database, filtered by skin type, severity, and ingredient compatibility. The recommendation module incorporates a rule-based engine enhanced with user feedback simulation for iterative refinement. Unlike existing models which focus solely on detection or static advice, this framework uniquely fuses AI-driven diagnostic precision with real-time, personalized product recommendations. The integration of deep learning with decision logic establishes a scalable pathway for intelligent, consumer-facing skincare solutions. Overall, the proposed system not only enhances diagnostic efficiency but also empowers users with clinically relevant and personalized skincare guidance. Figures depicting the CNN architecture, system flowchart, and sample recommendation outputs are included to illustrate the operational pipeline and outcomes.

Keywords: Smart Dermatology, Convolutional Neural Networks, Skin Anomaly Detection, Personalized Skincare, Artificial Intelligence in Healthcare, Product Recommendation System, Deep Learning, Image-Based Diagnosis