The invention discloses an e-commerce platform commodity recommendation algorithm, which comprises the following steps of: 1, obtaining operator original data: obtaining a user and a retrieval recordcopy from an operator big data system, including a user ID, a user number, keyword content, a retrieval date, retrieval times, commodity purchase information and commodity purchase times; The invention discloses an e-commerce platform commodity recommendation algorithm. The method comprises the steps of obtaining information of a user or purchase records of other users for judgment; related commodities are pushed; pushing of regional seasons and hot commodities by the user can be met; In addition, according to the invention, the structure is simple;, if the user does not express enough interest in the information pushed for the first time, the information is pushed for the second time; and according to the current season information and a plurality of pieces of commodity information in theregion where the user is located, the push content is adjusted, so that the problem of inaccurate information during first-time push is solved in time, the commodity selection time of the user is effectively shortened, and the user experience is improved.