The invention discloses a customer screening method based on big data, and aims to solve the technical problems that in the prior art, potential customers cannot be mined, the conversion rate of the customers is low, data is not crawled from a network, the data volume is relatively small, and the referable range is relatively small, so that the customer screening precision is not low during decision making or marketing. The method comprises the following steps: S1, crawling data from a website and an APP, and storing the data; S2, according to the crawled data, analyzing user basic information from the aspect of user static attributes, and performing user static attribute grade division. Data is crawled from the network, the cardinal number of the data size is larger, the screening precision of clients is higher, potential clients with low conversion rate are effectively deleted, the advertisement putting cost is reduced, higher profits are achieved, meanwhile, old clients are screened, and the quality of the old clients is graded, so that the advertisement putting efficiency is improved in a targeted manner. And a corresponding marketing strategy is made.