Paper Title
Network Traffic Forecasting Using Machine Learning and Statistical Regression Methods Combined With Different Time Lags

Abstract
In this study, different machine learning methods including Support Vector Machines (SVM), Radial Basis Function (RBF) Neural Network, M5P (a decision tree with linear regression functions at the nodes), Random Tree (RT), and Reduced Error Pruning Error (REPTree), and a statistical regression called Holt-Winters have been used to forecast the amount of network traffic in Transmission Control Protocol/Internet Protocol (TCP/IP) -based networks. Two different Internet Service Providers' (ISPs) traffic data have been utilized to develop traffic forecasting models. By using different time lags along with the aforementioned methods on the data sets, several Internet traffic forecasting models have been built. The performance of the forecasting models for the data sets has been assessed using Mean Absolute Percentage Error (MAPE). The results show that SVM and M5P based models usually perform better than other models. Keywords� Machine Learning, Time Series, Traffic Engineering, Time Lags.