Abstract
At present, there are more and more frauds in the financial field. The detection and prevention of financial frauds are of great significance for regulating and maintaining a reasonable financial order. Deep learning algorithms are widely used because of their high recognition rate, good robustness, and strong implementation. Therefore, in the context of e-commerce big data, this paper proposes a quantitative detection algorithm for financial fraud based on deep learning. First, the encoders are used to extract the features of the behaviour. At the same time, in order to reduce the computational complexity, the feature extraction is restricted to the space-time volume of the dense trajectory. Second, the neural network model is used to transform features into behavioural visual word representations, and feature fusion is performed using weighted correlation methods to improve feature classification capabilities. Finally, sparse reconstruction errors are used to judge and detect financial fraud. This method builds a deep neural network model with multiple hidden layers, learns the characteristic expression of the data, and fully depicts the rich internal information of the data, thereby improving the accuracy of financial fraud detection. Experimental results show that this method can effectively learn the essential characteristics of the data, and significantly improve the detection rate of fraud detection algorithms.
Highlights
With the development of the economy, there are more and more frauds in the financial field. e detection and prevention of financial fraud are of great significance for regulating and maintaining a reasonable financial order [1, 2]
Large database management systems are basic system software widely used by financial institutions. e use of data mining in large database systems is an advanced technical means for detecting financial fraud
The encoder is first used to extract the appearance and motion features of the behaviour, and in order to reduce the computational complexity, the feature extraction is constrained to the space-time volume of the dense trajectory
Summary
With the development of the economy, there are more and more frauds in the financial field. e detection and prevention of financial fraud are of great significance for regulating and maintaining a reasonable financial order [1, 2]. It can be used to monitor the transaction behaviour of multiple customers, employees, and financial transaction parties It is very helpful for discovering the internal connection of things hidden in the data. Fisch et al [8] proposed a data mining system that uses historical transaction data to build a neural network model to detect fraud. Merchant et al [9] proposed a neural network model based on merchant credit and ROC analysis. Menon et al [15] introduced a new theory of cost-sensitive machine learning into the decision tree and he found that this decision tree algorithm has traditional performance such as accuracy, recall rate is higher than existing algorithms and has a good expressiveness to the newly defined cost sensitivity in the field of credit card fraud. By establishing a model for e-commerce big data feature learning, mining the financial fraud behaviour characteristics of e-commerce big data, and inputting the features into the abnormal behaviour detection model, it can effectively, quickly, and accurately identify financial fraud behaviour, quantify fraud risk levels, and do well in advance relevant prevention work to avoid unnecessary losses caused by financial fraud
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
