Clothing similarity computation based on TLAC

Purpose To enhance the pleasure experience of clothes shopping online, finding satisfactory clothing and similar clothing recommendations to customers should be available and accurate. The purpose of this paper is to present a method for automatically computing the similarity between two apparels and giving an effective recommendation. Design/methodology/approach Based on a tabular layout of article characteristics the authors built a clothing information model to describe clothing. The clothing attributes are classified according to excavating features of the model. After the proposal of the computation algorithm for various attributes, an efficient similarity computation method is developed to obtain similar clothes with the given cloth. To prevent error and information omission during the computation, the analytic hierarchy process method and entropy method are adopted by the integrated weights as a control. Findings Clothing is a non‐rigid product which has a lot of crossover and complicated attributes and features. This paper found a tabular layout of article characteristics can explain the clothing clearly. Through experiments the authors found the weight of attributes to have a great influence on similar results during the similarity computation. Originality/value This paper presents a new way to describe clothing information, and present the algorithm for attributes computation.