Research on financing websites identification based on deep neural network

Abstract:

With the rapid development of Internet Finance, the existence of financing websites has become a much more serious problem for personal property safety. However, the traditional website recognition technology is only applicable to the website identification with some remarkable features, resulting in low efficiency of financing websites detection. This paper selects features from multiple dimensions and summarizes detection features into five categories: domain name features, search engines index features, tag features, image features, textual features, which greatly reflect the essential difference between the financing websites and other types of websites. Then a recognition model with deep neural network is proposed. In order to verify the validity of the model, a comparison experiment of our model with decision tree algorithm, support vector machine algorithm and K-Nearest Neighbor algorithm is designed. The experiments demonstrate that the accuracy and precision of the accuracy and precision of the proposed model is 95.9%, 98.7% respectively, and all kinds of evaluation indicators are better than the traditional machine learning algorithm. The results show that the proposed method can effectively detect the financing websites.