Data processing method, risk identification method, computer equipment and storage medium

Abstract

The embodiment of the invention discloses a data processing method. The method comprises steps of a first sample set used for training a first recognition model and at least one second sample set being acquired, and the at least one second sample set being used for training a second recognition model; determining that similarity data between the first sample set and at least one second sample setmeets preset requirements; combining the first sample set and at least one second sample set, obtaining a third sample set replacing the first sample set. According to the method, the first sample setis used as the input for training the first recognition model, so the samples for training the first recognition model are supplemented, the over-fitting problem of the first recognition model causedby too few samples in the first sample set is avoided, the recognition coverage rate of the first recognition model is improved, and the recognition effect is improved.

Description

technical field [0001] The present application relates to the technical field of data processing, and in particular to a data processing method, a risk identification method, a computer device, and a computer-readable storage medium. Background technique [0002] With the development of computer technology, technologies such as artificial intelligence and machine learning are increasingly being applied in practice. The machine learning method is a method in which a computer uses existing data, obtains a certain model through training, and uses the model to infer new instances. Therefore, the training process requires historically existing sample data, and the sample data will have a great impact on the prediction effect of the final model. [0003] In practice, for some businesses, historically existing samples are relatively scarce. For example, in e-commerce platforms, in order to prevent and control risks such as counterfeit goods, contraband, and fraud, and ensure busin...

AI Technical Summary

Problems solved by technology

[0004] The applicant has found through research that if the number of samples is too small, the assumption will become overly strict in order to obtain a consistent hypothesis, that is, one hypothesis can obtain a better fit than other hypotheses on the training data, but the assumptions outside the training data The data set cannot fit the data well, that is, the phenomenon of overfitting appears.

In short, during the training process of the model, too few samples will lead to the phenomenon of over-fitting of the model, which in turn leads to a low coverage rate of speculation with the model.

Images