The increasing demand for personalized skincare solutions highlights a significant gap: many consumers struggle to findsuitable products without professional guidance. While the commercial potential for tailored product recommendations is vast,a key challenge remains the lack of effective methods for skin profiling via image classification. To work on this challenge, adeep learning-based approach was developed. For this, we utilized the AUCMEDI framework, an open-source tool designedfor automated classification of medical images. The framework was applied to a dataset consisting of 3,203 facial images asselfies. A variety of architectures were trained to recognize and classify various skin features, including sagging skin, wrinkles,under-eye circles, redness, shine, pigment spots, acne, and pore size. The model’s performance was evaluated using theaverage absolute error (e) . By employing sophisticated image classification techniques, we have demonstrated promisingperformance in classifying sagging skin (e = 1.71) and wrinkles (e = 1.40). While achieving satisfactory results for under-eyecircles(e = 0.32), redness (e = 2.22), shine (e = 0.23), and pigment spots (e = 2.20), we encountered greater challenges inclassifying acne (e = 2.59) and pore size (e = 2.57). This paper introduces a novel approach to automated skin analysis andprofiling, which lays the groundwork for more objective tools in dermatological assessment.