Development of Machine Learning Based Fraudulent Website Detection Scheme

The development of mobile computing and e-commerce has greatly changed traditional transactions and grown online shopping. People are buying and selling goods on websites or social platforms. However, there are many malicious and counterfeit products on fraudulent websites to deceive consumers and make high improper profits. Due to the obvious increase in the number of such fraudulent websites, it is difficult to identify and detect these websites by manual inspection. In order to solve this problem, we propose an intelligent detection mechanism by using a machine learning approach to classify fraudulent websites. We use data set containing 300 legitimate websites, 300 fraudulent websites, and 15 features for training. In two machine learning algorithms, Random Forest and Deep Neural Networks, we divided the training set and the test set in a ratio of 8:2. Finally, the prediction is compared with the previous research results. The experimental results show that the RF accuracy of the random forest algorithm is 99.3% which is better than other deep neural networks algorithms.