<![CDATA[The rapid evolution of ransomware attacks necessitates robust and scalable detection mechanisms to safeguard digital assets. This study leverages the Bitcoin Ransomware Dataset, comprising 2,916,697 transactions, to evaluate the effectiveness of the Random Forest algorithm in classifying ransomware-related activities. Through comprehensive preprocessing, including feature encoding and standardization, and exploratory data analysis (EDA), the dataset is prepared for modeling. The Random Forest model achieves an overall accuracy of 99%, demonstrating exceptional performance in identifying the majority class. However, challenges persist in classifying minority classes, highlighting the impact of class imbalance. Feature importance analysis reveals that attributes such as income, weight, and length play pivotal roles in the classification process. The study underscores the potential of Random Forest for ransomware detection while emphasizing the need for advanced techniques to address class imbalance and improve minority class performance.]]>
Copyrights © 2025
