Data preprocessing method and device for business model

Abstract

The invention relates to a data preprocessing method and device for a business model. The embodiment of the invention provides a novel service model for processing classification services. The servicemodel is realized through a plurality of deep networks, and in the plurality of deep networks, the importance of each service feature for the corresponding classification category can be fully considered in each deep network by introducing feature expression vectors for describing different feature values and each layer label vector corresponding to each classification category. When the businessmodel is used for determining the target category; according to the technical scheme, the possibility that each classification category serves as the target category of the to-be-processed service data can be determined according to the classification category, so that the accuracy of the service model is improved, the service processing result of the service model has traceability due to the fact that the importance coefficient of the corresponding service feature is determined in each deep network, and the use experience is improved.

Description

technical field [0001] One or more embodiments of this specification relate to the field of computer technology, and in particular to a method and an apparatus for processing business data by performing data preprocessing on a business model and using the business model after data preprocessing. Background technique [0002] With the development of machine learning technology, Deep Neural Network (DNN) is favored by those skilled in the art because it imitates the way of thinking of the human brain and has better results than simple linear models. A deep neural network is a neural network with at least one hidden layer that can provide modeling for complex nonlinear systems, thus improving the capabilities of the model. However, conventional deep neural network methods cannot give interpretability due to complex network structures. [0003] As an example, assume that in the lending scenario, the risk level of a user’s loan is judged. If the user’s risk is high, the risk of ...

AI Technical Summary

Problems solved by technology

In conventional technology, if the rules are manually designed or a simple linear classification model is used, the prediction accuracy is usually poor; while the traditional deep neural network has high accuracy, but it cannot provide good explanations, such as the explanation of why users cannot borrow , such as historical loan defaults, very low frequency of use of related financial platforms (new users), frequent illegal parking of shared bicycles, etc., if a reasonable explanation cannot be given at this time, it will affect the user experience

Images