Implementation of ML Algorithm for Spyware Detection System Using SVM with KNN Algorithm for Comparison of Accuracy

The research examines the Support Vector Machines (SVM) and K-Nearest Neighbor (KNN) machine learning algorithms with the goal of using machine learning to detect malware and mitigate cybersecurity threats. Utilizing the malware dataset and the SVM and KNN methods, which consists of 500 rows and 6 attribute columns, the accuracy of spyware detection is determined. This dataset was collected from the well-known kaggle website. Python 3. 12 is the programming dialect used to run the code in IDLE shell. The clinical calculator is used for estimating the sample size. Groups 1 and 2 have a computed sample size of 500 with an alpha 80% power, a 95% confidence level, and a threshold value of 0.05. The Data Analytics lab is where research is done. Using the IBM SPSS statistical software, version 27, the accuracy of the SVM algorithm is compared to that of the KNN method. When comparing the Support vector machines’ mean accuracy to the K-Nearest Neighbors algorithm, the results show a substantial improvement.