Claim Missing Document
Check
Articles

Found 2 Documents
Search

Customer churn prediction in the case of telecommunication company using support vector machine (SVM) method and oversampling Urrahman, Dhiya; Winanto, Raffi; Widyatama, Thierry
Journal of Student Research Exploration Vol. 2 No. 2: July 2024
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/josre.v2i2.253

Abstract

hurn is the act by which a customer withdraws from service, including service provider-initiated churn and customer-initiated churn. Churn is a big challenge for companies, especially churn-prone enterprise sectors such as telecommunications. Churn can affect both revenue and reputation if occurs for negative reasons. This study aims to predict customer churn in a telecommunication company dataset, investigating the impact of various variables and classes on churn occurrences to inform strategic decision-making for businesses. The Support Vector Machine (SVM) model is employed, and dataset imbalance is addressed through oversampling techniques, specifically Synthetic Minority Over-sampling Technique (SMOTE) and random oversampling (ROS). Three SVM models are created with different training datasets (normal, SMOTE, ROS), yielding varying results. The normal dataset achieves the highest accuracy at 92%, outperforming SVM with ROS (89%) and SVM with SMOTE (87%). However, the normal dataset exhibits lower sensitivity compared to both oversampling techniques. The study identifies the cause of decreased accuracy in oversampling and low sensitivity in the normal dataset. The novelty of this research lies in testing the SVM model's ability to surpass the accuracy of previous models on the same dataset and in exploring the unique impact of oversampling in churn prediction.
Improving Attack Detection in IoV with Class Balancing and Feature Selection Widyatama, Thierry; Rizqa, Ifan; Rafrastara, Fauzi Adi
Journal of Applied Informatics and Computing Vol. 9 No. 2 (2025): April 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i2.9080

Abstract

The Internet of Vehicles (IoV) represents a specialized application of the Internet of Things (IoT), enabling vehicles to communicate with their surrounding infrastructure to enhance transportation safety and efficiency. However, IoV systems are susceptible to various cyberattacks, including Denial of Service (DoS) and spoofing attacks, which necessitate effective and efficient detection mechanisms. This study investigates the enhancement of detection efficiency for DoS and spoofing attacks in IoV by employing Ensemble Learning methods combined with feature selection techniques. The selected feature selection methods include Information Gain Ratio, Chi-Square (X²), and Fast Correlation-Based Filter (FCBF). The CICIoV2024 dataset, utilized in this study, was balanced using the Random Under Sampling technique to address data imbalance issues. The ensemble algorithms evaluated in this research comprise Random Forest, Gradient Boosting, and XGBoost. Results indicate that all three algorithms achieved high accuracy and F1 scores, reaching 0.985. Moreover, the application of feature selection significantly reduced computational time without compromising detection performance. These findings are expected to contribute to the advancement of IoV security systems in the future.