In the era of digital globalization and burgeoning online shopping trends, the clothing e-commerce sector is experiencing exponential growth. However, in the midst of an abundance of options available, consumers often find themselves overwhelmed when selecting the perfect outfit. Current websites typically adopt a generalized approach, predominantly promoting best-selling or popular items, thereby neglecting the essence of customer-centricity and individuality. Consequently, there is a pressing demand for a streamlined and dependable system that aids users in discovering suitable products efficiently. To address this need, a hybrid recommender system (RS) has been proposed in this work. This system leverages both auto-encoder and K-nearest neighbor algorithms to enhance the recommendation process. By integrating user input data, the system can effectively tailor suggestions to match individual preferences and styles. Such personalized recommendations not only save time for users but also contribute to increased sales by fostering a more engaging and satisfying shopping experience. Ultimately, this innovative approach bridges the gap between the vast array of choices available and the discerning needs of consumers, facilitating informed decision-making and fostering a deeper connection between shoppers and their desired apparel.