Commodity recommendation method and system based on big data

The invention provides a commodity recommendation method and system based on big data, and relates to the technical field of information pushing. According to the method and the device, groups with similar purchase behaviors are mined based on the historical behavior data of the user, and the commodity recommendation set which meets personal potential requirements of the customer and has a reference value is obtained; based on the commodity recommendation set and the click data of the target user at this time, re-calculating the recommendation score of each commodity in different scenes (shopping scenes formed by different ages, occupations and genders of the target user), and carrying out descending sort to obtain the commodity recommendation set; therefore, the commodity recommendation system can recommend proper commodities to the user in a proper scene and select personalized commodities which the user wants to purchase from a large number of commodities, so that the user can obtain the products required