A Comparative Study of Machine Learning Methods for Generation of Digital Forensic Validated Data

A number of machine learning algorithms are avail-able for detection of different types of network anomalies. How-ever, network anomalies vary in their requirement for detection and there is no general method or algorithm that is applicable to all types of anomalies which may occur in a network. The paper divulges the application of different available methods in comparison mode and analyses the rationale of the algorithms. Freely available databases are used for study and used as a benchmark for testing different methods of network anomalies. The benchmarks are used for testing accuracy. Such accuracy threshold indicates the required data validation. Validated data may be used forensic purpose. The data for Digital forensic must pass a threshold value from the test data. Determination of efficiency of methods is additional analytical aspect of the paper that is achieved in Python coding and in well formulated steps. The paper gives an overview of the process for finding network anomalies and data accuracy for digital forensic use.