Shanghai Icekredit, Inc.

Wan Duan

Lingyun Gu

Minqi Xie

Yang Zhang

Yizeng Huang

Shuhui Chen

Kai Zhang

Zhenyu Wang

A data processing method includes: obtaining first sample data, and determining a target model and a feature set corresponding to the target model; obtaining second sample data, and dividing the second sample data into a development data set and a validation data set based on a predetermined proportion or a predetermined chronological order; respectively determining final sample data of the first sample data and retained sample data of the development data set based on the target model, the feature set corresponding to the target model, the first sample data, the development data set and the validation data set; and merging the final sample data and the retained sample data to obtain a modeling data set corresponding to a first business project. A data processing apparatus, and a computer device for implementing the data processing method are further provided.

Data processing method and apparatus, and computer device

A business data processing method includes: step S1: extracting domestic business sample data; step S2: selecting a sample data set S by training a model; step S3: extracting overseas business sample data; step S4: merging the data set S and a data set T to obtain a data set A; step S5: setting an initial sample weight; step S6: setting a variable for a quantity of iterations; step S7: training the model based on a current weight to obtain a model At; step S8: calculating a loss et of the model At in the data set T; step S9: caching the model At and the loss et; step S10: updating a sample weight; step S11: updating the quantity of iterations t=t+1; step S12: determining whether a termination condition is met; and step S13: when the termination condition is met, determining a final model.

Business data processing method and computer device

A business prediction method includes: obtaining a first business sample set and a second business sample set; performing training based on the first business sample set and the second business sample set to obtain a business prediction model, and predicting received to-be-predicted business information based on the business prediction model to obtain a business prediction result corresponding to the received to-be-predicted business information. A business prediction apparatus is further provided. The business prediction method and the business prediction apparatus take into account data features of some business samples of being rejected in a business validation, while considering business samples of passing the business validation. This restores a business scenario, reduces the waste of costs of the rejected samples, and balances demands for a modeling sample and a rejected sample reasonably when there are insufficient samples of passing the business validation.

Business prediction method and apparatus

Growing community of inventors

Shanghai, China

Wan Duan