The invention provides an anti-fraud decision model construction method based on multi-dimensional data flow. The method comprises the following steps: S1, receiving a registration request of a user,and allocating function authority to the user; S2, configuring an anti-fraud decision model in a user-defined mode, and the anti-fraud decision model comprising a rule set, a scoring model and associations between the rule set and the rule set, between the rule set and the scoring model and between the scoring model and the scoring model; and S3, storing the configured anti-fraud decision model asa template into a decision model template market, and supporting editing and storage of a decision set in the anti-fraud decision model. According to the method, services such as anti-fraud identification, preposed risk control prevention, accurate risk identification and professional information verification are provided for a business system, a user can construct a decision model based on a self-owned rule set or a scoring model, safe operation of self-owned businesses is ensured, and meanwhile, the influence of false information on subsequent loan businesses and the loss caused by fraud requests are reduced.