Web Bot Detection Using Mouse Movement

Non-Legitime traffic in terms of automated internet bot traffic is a long-standing problem causing a huge economic impact and lack of trust in companies and administrations worldwide. For years, Artificial Intelligence and especially Machine Learning have been key players fighting and helping the stakeholder to analyze and detect fraud instances automatically. However, it does not exist a reliable ground truth public dataset to evaluate and compare the proposed methodologies in the literature. In this ongoing study, a public dataset consisting of human and bad-bot web mouse movements extracted from real bot engines is being developed. When finished, it will be uploaded publicly. In addition, this dataset is evaluated using two Machine Learning models. The first is gradient boosting algorithm based on tree classifiers and the second a Recurrent Neural Network. Both models obtain excellent preliminary results.