Effective Machine Leaning Based Malware detection and Classification Using Improved Voting Method based Decision Tree

Malware poses a significant threat to individuals, organizations, and even nations. Developing effective detection and classification models helps in mitigating these threats by identifying and neutralizing malicious software before it can cause harm. In this paper, proposed the Machine learning (ML) based improved Voting method based decision tree is used to classify and detecting the malware poses, the model training is conducting on CICI-Melmem2020 dataset. The dataset has unwanted noise, Null values, infinite values they are normalized in the preprocessing stage. Continuously build a smaller set of features from a larger set is utilized for extract the features subsequently the ranking technique is used to select the features. Finally, the proposed VM- DT classifier is used to classify and detecting the malware poses. this approach's numerical validation yielded an Accuracy of 99.98% and Precision of 99.98% and Recall of 99.97%. the suggested method outperforms all the current methods, as demonstrated by a comparison of Logistic Regression-Feature Ranking Technique (LR-FRT), Massive algorithm of Support Vector Machine (MA-SVM), and Android Malware Detection Naive Bayes (AMD-NB).