The rapid growth of big data technology has become a major trend affecting the pattern of world development.Big data criminal investigation is a new type of criminal detection used extensively in the course of police ...The rapid growth of big data technology has become a major trend affecting the pattern of world development.Big data criminal investigation is a new type of criminal detection used extensively in the course of police practice at home and abroad.Its emergence indicates a trend in criminal justice towards ensuring security at the expense of privacy and exchanging rights for information.Big data criminal investigation highlights the backwardness and dysfunction of the traditional framework of legal norms,evident in doubts about the legal attributes of such investigation and the obvious limitations of techniques for distinguishing data content from metadata.This leaves a vacuum in the regulation of investigative power at the preliminary stage of investigation.Big data criminal investigation itself is a doubleedge sword;in order to forestall the possible abuses it may entail in terms of deep and broad interventions in basic civil rights,big data criminal investigation should be brought under the necessary legal control.We therefore propose adopting a dual regulatory approach comprising investigative and data norms,selectively adopting the traditional normative framework of the principle of legality and the principle of proportionality,and at the same time supplementing it with other legal principles and mechanisms concerning the protection of personal information and data.展开更多
Personal credit risk assessment is an important part of the development of financial enterprises. Big data credit investigation is an inevitable trend of personal credit risk assessment, but some data are missing and ...Personal credit risk assessment is an important part of the development of financial enterprises. Big data credit investigation is an inevitable trend of personal credit risk assessment, but some data are missing and the amount of data is small, so it is difficult to train. At the same time, for different financial platforms, we need to use different models to train according to the characteristics of the current samples, which is time-consuming. <span style="font-family:Verdana;">In view of</span><span style="font-family:Verdana;"> these two problems, this paper uses the idea of transfer learning to build a transferable personal credit risk model based on Instance-based Transfer Learning (Instance-based TL). The model balances the weight of the samples in the source domain, and migrates the existing large dataset samples to the target domain of small samples, and finds out the commonness between them. At the same time, we have done a lot of experiments on the selection of base learners, including traditional machine learning algorithms and ensemble learning algorithms, such as decision tree, logistic regression, </span><span style="font-family:Verdana;">xgboost</span> <span style="font-family:Verdana;">and</span><span style="font-family:Verdana;"> so on. The datasets are from P2P platform and bank, the results show that the AUC value of Instance-based TL is 24% higher than that of the traditional machine learning model, which fully proves that the model in this paper has good application value. The model’s evaluation uses AUC, prediction, recall, F1. These criteria prove that this model has good application value from many aspects. At present, we are trying to apply this model to more fields to improve the robustness and applicability of the model;on the other hand, we are trying to do more in-depth research on domain adaptation to enrich the model.</span>展开更多
文摘The rapid growth of big data technology has become a major trend affecting the pattern of world development.Big data criminal investigation is a new type of criminal detection used extensively in the course of police practice at home and abroad.Its emergence indicates a trend in criminal justice towards ensuring security at the expense of privacy and exchanging rights for information.Big data criminal investigation highlights the backwardness and dysfunction of the traditional framework of legal norms,evident in doubts about the legal attributes of such investigation and the obvious limitations of techniques for distinguishing data content from metadata.This leaves a vacuum in the regulation of investigative power at the preliminary stage of investigation.Big data criminal investigation itself is a doubleedge sword;in order to forestall the possible abuses it may entail in terms of deep and broad interventions in basic civil rights,big data criminal investigation should be brought under the necessary legal control.We therefore propose adopting a dual regulatory approach comprising investigative and data norms,selectively adopting the traditional normative framework of the principle of legality and the principle of proportionality,and at the same time supplementing it with other legal principles and mechanisms concerning the protection of personal information and data.
文摘Personal credit risk assessment is an important part of the development of financial enterprises. Big data credit investigation is an inevitable trend of personal credit risk assessment, but some data are missing and the amount of data is small, so it is difficult to train. At the same time, for different financial platforms, we need to use different models to train according to the characteristics of the current samples, which is time-consuming. <span style="font-family:Verdana;">In view of</span><span style="font-family:Verdana;"> these two problems, this paper uses the idea of transfer learning to build a transferable personal credit risk model based on Instance-based Transfer Learning (Instance-based TL). The model balances the weight of the samples in the source domain, and migrates the existing large dataset samples to the target domain of small samples, and finds out the commonness between them. At the same time, we have done a lot of experiments on the selection of base learners, including traditional machine learning algorithms and ensemble learning algorithms, such as decision tree, logistic regression, </span><span style="font-family:Verdana;">xgboost</span> <span style="font-family:Verdana;">and</span><span style="font-family:Verdana;"> so on. The datasets are from P2P platform and bank, the results show that the AUC value of Instance-based TL is 24% higher than that of the traditional machine learning model, which fully proves that the model in this paper has good application value. The model’s evaluation uses AUC, prediction, recall, F1. These criteria prove that this model has good application value from many aspects. At present, we are trying to apply this model to more fields to improve the robustness and applicability of the model;on the other hand, we are trying to do more in-depth research on domain adaptation to enrich the model.</span>
