A small neighborhood fabric recommender system based on user historical behavior and preference

In the current landscape, textile companies need rapid, precise, and personalized assistance, especially as digitalization and information, such as e-commerce and websites, are developing rapidly. Textile enterprises can mine user preferences to make personalized recommendations of appropriate textile fabrics; this is not only in keeping with current trends, but more importantly, can control production costs and improve user satisfaction. To support the transformation of textile enterprises to a small-batch and multi-variety business model, this paper proposes a fabric recommendation system; specifically, a fabric recommender system based on user historical behavior and preference is proposed. The proposed method is mainly based on the integration of preference, user activity, and rating; firstly, according to the fabric products purchased by the user, the features of the fabric are mined using a neural network to obtain the user’s preferences; secondly, neighbors with similar user behaviors are found according to similarity in users’ activity; and finally, understanding of the fabric is enhanced through a matrix based on the fabric ratings of the user. A focus on recommendation algorithm parameterization, including selection, thresholding, and neighborhood optimization, elevates the recommendation quality. A user–fabric dataset was used for experimental verification, and included the user’s purchase score of the fabric and the image of the fabric. Comparative analyses demonstrate superior precision with fewer neighborhoods, achieving a score of up to 0.93. Our research provides insights into user behavior and personalization, guiding future recommender system design and optimization.