With the development of e-commerce, credit card fraud is also increasing. At the same time, the way of credit card fraud is also constantly innovating. Support Vector Machine, Logical Regression, Random Forest, Naive Bayes and other algorithms are often used in credit card fraud identification. However, the current fraud detection technology is not accurate, and may cause significant economic losses to cardholders and banks. This paper will introduce an innovative method to optimize the support vector machine by cuckoo search algorithm to improve its ability of identifying credit card fraud. Cuckoo search algorithm improves classification performance by optimizing the parameters of support vector machine kernel function (C, g). The results demonstrate that CS-SVM is superior to SVM in Accuracy, Precision, Recall, F1-score, AUC, and superior to Logistic. Regression, Random Forest, Decision Tree, Naive Bayes, whose accuracy is 98%.

Credit card fraud is the new financial fraud crime accompanied by the gradual development of the economy which causes billions of dollars of losses every year. Credit card fraud case not only seriously violated the cardholder benefits and financial institutions, but also undermined the credit management order. However, fraudsters keep exploring new crime strategies constantly which exacerbates the crime rate of fraud. Thus, a predictive model for credit card fraud detection is essential to minimize its losses. By distinguishing between fraud and non-fraud, machine learning is one of the most efficient solutions for detecting fraud. Support vector machines have proven to be a novel algorithm with excellent performance. Nevertheless, the performance of SVM depends largely on the correct choice of model parameters (C and g), which could cause that the false positive was very high if the kernel function type and parameter cannot be selected properly. In this paper, based on the real transaction data of the credit card business, firstly, it will find the optimal kernel function suitable for the data set. Secondly, this paper will propose the method of optimizing the support vector machine parameters by the cuckoo search algorithm, genetic algorithm and particle swarm optimization algorithm. Last but not least, the Linear kernel function was found to be the best kernel function with an accuracy rate of 91.56%. Furthermore, the Radial basis function is used to optimize the kernel function, which can improve the accuracy from 42.86% to the highest accuracy rate of 98.05%. Compared with CS-SVM and GA-SVM, PSO-SVM has the best overall performance.

A few decades ago, the protection of personal information was basically in the state of none, with more and more problems due to personal information, such as the use of information to achieve fraud and the use of false information to publish bad information, causing great property losses to people’s lives. People only began to have awareness of the protection of personal information. After this, the civil law protection of personal information in IoT management has been developed. In this paper, we present a comparative analysis of the application of data sharing and protection of personal information based on the Internet of Things (IoT) management, as well as the sharing mechanisms used in data information, the protection of information security, and the drawbacks, which explains the safety information analysis of personal information in the case of data sharing and the calculation method used by the IoT in data sharing. A comparative study found that on the basis of IoT management, the security and concealment of personal information have been improved by about 20%. In practical application, IoT also brings great convenience in information data sharing. It increases the efficiency of operation, reduces losses, and to a certain extent guarantees the security of people’s individual information.

No abstract

Currently, cloud computing provides users all over the globe with Information and Communication Technology facilities that are utility-oriented. This technology is trying to drive the development of data center design by designing and building them as networks of cloud machines, enabling users to access and run the application from any part of the globe. Cloud computing provides considerable benefits to organizations by providing rapid and adaptable ICT software and hardware systems, allowing them to concentrate on creating innovative business values for the facilities they provide. The right to privacy of big data has acquired new definitions with the continued advancement of cloud computing, and the techniques available to protect citizens’ personal information under administrative law have managed to grow in a multitude. Because of the foregoing, internet fraud is a new type of crime that has emerged over time and is based on network technology. This paper analyzed and studied China’s internet fraud governance capabilities, and made a comprehensive evaluation of them using cloud computing technology and the Analytic Hierarchy Process (AHP). This paper discussed personal information security and the improvement of criminal responsibility from the perspective of citizens’ information security and designed and analyzed cases. In addition, this paper also analyzed and studied the ability of network fraud governance in the era of cloud computing. It also carried out a comprehensive evaluation and used the fuzzy comprehensive evaluation method to carry out the evaluation. A questionnaire survey was used to survey 100 residents in district X of city Z and district Y of the suburban area. Among the 100 people, almost all of them received scam calls or text messages, accounting for 99%, of which 8 were scammed. Among the people, more than 59.00% of the people expressed dissatisfaction with the government’s Internet fraud satisfaction survey. Therefore, in the process of combating Internet fraud, the government still needs to step up its efforts.