A Master's Thesis in computer science Dept. proposes an Effective Detection System to Monitor the behavior of users of the banking system

A master's thesis in Dept. of Computer Science at U.O.T.  proposes an Effective and Modified Detection System (IDS) to monitor and classify the behavior of users of the banking system by applying three machine learning algorithms as classifiers, the first classifier is the Naïve Bayes (NB) algorithm, and the second classifier is the decision tree algorithm.

(DT), the third classifier is K-Nearest Neighbor (KNN) which represents the end result provider as it gives the end result of the system which represents the nature of the user behavior whether it is normal or suspicious behavior.

The Thesis presented by the/  student Wissam Saleh Mahdi, entitled, tracking user behavior for intrusion detection systems using machine learning algorithms, discussed a banking system that contains 2324 users where their behavior is tracked using the User Behavior Tracking System (IDS) to see if the users' behavior is normal or suspicious.

Experimental results showed that the proposed system has a high accuracy of grading between normal and suspicious user behavior in terms of Accuracy of 99.0%, Precision of 98.9% and DR of 99.9%.

The discussion committee consisted of:-

1- Prof. Dr.  Alaa Kadhim / Chairman

2- Asst. Prof. Dr. Iyad Raudhan/ Member

3- Asst. Prof. Dr. Wathiq Najah/ Member

4- Asst. Prof. Dr. Abeer Tariq/ supervisor