Dressing recommendation method and apparatus are described. The dressing recommendation method includes: obtaining a first feature vector of each of a plurality of pieces of clothes to be recommended, the first feature vector including at least proportions of materials used in said each piece of clothes and a total weight of said each piece of clothes; learning the first feature vector by means of a machine learning model to obtain a second feature vector representing a target attribute of said each piece of clothes to be recommended, wherein the target attribute indicates a temperature range in which the piece of clothes is suitable for wearing; recommending clothes to a user according to the current weather information and the target attributes of the plurality of pieces of clothes to be recommended.