Advanced New Technologies Co., Ltd.

Licui Gao

Lujia Chen

Jun Zhou

Wenbiao Zhao

Weiqiang Wang

Xiaoxi Ji

Wenjing Fang

Methods and apparatus, including computer programs encoded on computer storage media, for monitoring resource transfer are provided. One of the methods includes: by a server, receiving a resource deposit request from a resource deposit initiator; performing, using a first risk identification model, a first risk identification on the target account according to the resource deposit request to obtain a first risk identification result; receiving a resource withdrawal request from a resource withdrawal initiator, and the resource withdrawal request requesting a resource withdrawal from the target account to the recipient account; performing, using a second risk identification model, a second risk identification on the target account according to the resource withdrawal request to obtain a second risk identification result; and determining, using a third risk identification model, a resource transfer risk monitoring result of the target account according to the first risk identification result and the second risk identification result.

Resource transferring monitoring method and device

Implementations of the present specification disclose methods, devices, and apparatuses for determining a feature interpretation of a predicted label value of a user generated by a GBDT model. In one aspect, the method includes separately obtaining, from each of a predetermined quantity of decision trees ranked among top decision trees, a leaf node and a score of the leaf node; determining a respective prediction path of each leaf node; obtaining, for each parent node on each prediction path, a split feature and a score of the parent node; determining, for each child node on each prediction path, a feature corresponding to the child node and a local increment of the feature on the child node; obtaining a collection of features respectively corresponding to the child nodes; and obtaining a respective measure of relevance between the feature corresponding to the at least one child node and the predicted label value.

GBDT model feature interpretation method and apparatus

A model integration method and device are provided. The method includes: obtaining an integrated model, the integrated model having one integrated output value and a plurality of input values, the plurality of input values corresponding to a plurality of output values of a plurality of independent models; performing one or more iterations of optimizing process until a preset iteration stop condition is satisfied: acquiring a prediction output by the integrated model based on a preset test event set; determining an index value of the integrated model based on the prediction output, the index value indicates a performance evaluation of the integrated model; if the index value fails to meet a preset performance requirement; after the preset iteration stop condition is satisfied, determining the integrated model as acceptable.

Growing community of inventors

Hangzhou, China

Licui Gao