This paper focuses on the effective classification of the behavior of users accessing computing devices to authenticate them. The authentication is based on keystroke dynamics which captures the user's behavioral biometric and applies machine learning concepts to classify them. The users type a strong passcode ".tie5Roanl" to record their typing pattern. In order to confirm identity anonymous data from 94 users were collected to carry out the research. Given the raw data, features were extracted from the attributes based on the button pressed and action timestamp events. The Support Vector Machine (SVM) classifier uses multi-class classification with one vs. one decision shape function to classify different users. To reduce the classification error, it is essential to identify the important features from the raw data. In an effort to confront the generation of features from attributes an efficient feature extraction algorithm has been developed, obtaining high classification performance are now being sought.

In this paper, we have applied minimum redundancy maximum relevance mRMR feature selection to increase the classification performance metrics and to confirm the identity of the users based on the way they access computing devices. From the results, we conclude that touch pressure, touch size and coordinates effectively contribute to identifying each user. The research will contribute significantly to the field of cyber-security by forming a robust au thentication system using machine learning algorithms.