Network platform data resource value evaluation method

Abstract

The invention relates to a network platform data resource value evaluation method. The method comprises the following steps: 1, constructing a data resource value evaluation index system in a networkplatform transaction environment; 2, determining an evaluation index weight based on an entropy correction G1 method; 3, pre-screening the transaction data resources of the platform based on a grey correlation analysis method; screening out transacted data resources of which the association degree with the pre-evaluated data resources is greater than or equal to a threshold value to form a model sample set T; 4, selecting a random forest model as a basic model of network platform data resource value evaluation, and constructing a data resource value evaluation model by utilizing the sample setT; and inputting each evaluation index of the pre-evaluated data resource into the data resource value evaluation model, and taking the average value of the output value of each regression tree as the data resource value evaluation result of the data resource value evaluation model. According to the method, the accuracy of data resource value prediction can be remarkably improved, the calculationamount of the RFR model can be reduced, and the training efficiency of the RFR model is improved.

Description

technical field [0001] The invention belongs to the field of resource value evaluation, and relates to a method for evaluating the value of network platform data resources based on gray relational analysis-random forest regression. Background technique [0002] In the era of data explosion, data not only plays the role of recording and archiving, but multi-source and cross-domain data association analysis forms more complete knowledge and deeper intelligence, greatly enhances the future prediction function, and data resources serve as tradable The open circulation of commodities has increasingly become a common understanding and an objective demand. According to the "2018 China Big Data Development Report" released by the State Information Center, the scale of China's big data trading market will reach 73.1 billion yuan in 2020. Under the trend of "Internet +", online platforms have become important trading channels and media, and data trading platforms such as Factual, BDE...

AI Technical Summary

Problems solved by technology

Some scholars have also proposed the research idea of ​​artificial intelligence method evaluation, and the use of neural networks to build data resource value evaluation evaluation models has become a research trend in this field, but the relevant research is not yet rich, and there is a lack of empirical testing

Images