The growth of android applications is causing a threat and a serious issue towards Android’s security. The number of malware targeting the Android operating system is increasing daily. As a result, in recent days the traditional ways that are being used to detect malware are not able to defend alone against the rapid development of hackers attacking techniques and novel malware. This capstone project focuses on using predictive analytics toward detecting malware from the network traffic. In this capstone project, we aim to train and test our data to find the best machine learning model with the highest accuracy of detecting malware in the network traffic. Through a variety of machine learning algorithms and models, we focused on 5 models starting with the logistic regression that was successfully able to predict malware by 67%. Moving to the decision tree that was effectively able to predict malware by 69% which was exactly equal to the random forest prediction ability. The AdaBoost came about 84% exactness, and KNN came with the highest anticipation of 86% between all the models. This shows us the advantage of adopting predictive analytics in malware detection within the traditional approaches to build a strong and defendable Android operating system against malware.

Publication Date


Document Type

Master's Project

Student Type


Degree Name

Professional Studies - City Sciences (MS)

Department, Program, or Center

Graduate Programs & Research (Dubai)


Sanjay Modak

Advisor/Committee Member

Boutheina Tlili


RIT Dubai