Optimized Website Traffic Forecasting with Automatic Models and Optuna
A Study in Machine Learning dan Big Data Analytics
DOI:
https://doi.org/10.52731/liir.v005.204Keywords:
Facebook Prophet, Foreasting, NeuralProphet, Website Traffic, Time SeriesAbstract
Although time-series forecasting has emerged as a key area of interest in recent years for analyzing historical data to make predictions about future trends, accurately forecasting web traffic can be challenging due to the dynamic nature of the internet and the many factors that can influence user behavior. Existing traffic flow prediction approaches primarily use simple models that are often inadequate for real-world applications. This research aims to develop an optimized machine learning model using FB-Prophet and NeuralProphet for forecasting website traffic and to compare their relative performance and effectiveness in predicting web traffic. This study aims to develop an optimized machine learning model using FB-Prophet and NeuralProphet for forecasting website traffic and to compare their performance in predicting web traffic. Our study found that both FB-Prophet and NeuralProphet models performed better than the simple models used in existing traffic flow prediction approaches. However, the NeuralProphet model outperformed FB-Prophet in terms of accuracy and computational efficiency. The best result obtained from the study was achieved by the NeuralProphet model, which had a Mean Average Error (MAE) of 25.61, Mean Square Error (MSE) of 1354, Root Mean Square Error (RMSE) of 5.060, and a Coefficient of Determination (R2) of 0.882, indicating its superior performance in accurately forecasting website traffic. The results suggest that an optimized machine learning model using NeuralProphet can be an effective way to forecast website traffic and help businesses and organizations better understand web traffic patterns.
References
Y.-C. Tsao, Y.-K. Chen, S.-H. Chiu and J.-C. Lu, "An innovative demand forecasting approach for the server industry," Elsevier, vol. 110, 2022.
T. Shelatkar, S. Tondale and S. Yadav, "Web Traffic Time Series Forecasting using ARIMA and LSTM RNN," in ITM Web of Conferences, Nerul, 2020.
N. Suresh, B. Priya, M. S. Teja, B. S. Krishna and G. Lakshmi, "Historical Analysis and Forecasting of Stock Market Using FBPROPHET," South Asian Journal of Engineering and Technology, pp. 152-157, 2022.
V. Kramar and V. Alchakov, "Time-Series Forecasting of Seasonal Data Using MachineLearning Methods," MDPI, vol. 16, p. 248, 2023.
D. Shah, P. Sanghani and M. Rahevar, "Short-Term Traffic Flow Prediction for an Urban Highways using Time Series Forecasting Model," International Journal of Innovative Science and Research Technology, vol. 6, no. 12, pp. 134-140, 2021.
B. Lim and S. Zohren, "Time-series forecasting with deep learning: A survey," Philosophical Transactions of the Royal Society, vol. 379, 2021.
C. B. A. Satrio , W. Darmawan, B. U. Nadia and N. Hanafiah, "Time series analysis and forecasting of coronavirus disease in Indonesia using ARIMA model and PROPHET,"in International Conference on Computer Science and Computational Intelligence,Jakarta, 2020.
H. T. Rauf, . M. I. U. Lali, M. A. Khan and S. Kadry, "Time series forecasting of COVID-19 transmission in Asia Pacific countries using deep neural networks,"Springer, p. 733–750, 2021.
O. Triebe, H. Hewamalage and P. Pilyugina, "NeuralProphet: Explainable Forecasting at Scale," pp. 1-40, 2021.
O. Triebe, L. R and R. R, "AR-Net: A simple Auto- Regressive Neural Network fortime-series," Arxiv, vol. D, pp. 1-12, 2019.
Z. Cui, R. Ke, Z. Pu and X. Ma , "Learning traffic as a graph: A gated graph wavelet recurrent neural network for network-scale traffic prediction," Elsevier, vol. 115, 2020.
S. Patandung and I. Jatnika, "The FB Prophet Model Application to the Growth Prediction of International Tourists in Indonesia during the COVID-19 Pandemic," International Research Journal of Advanced Engineering and Science, vol. 6, no. 2, 2021.
K. Arai, "Data Retrieval Method based on Physical Meaning and its Application for Prediction of Linear Precipitation Zone with Remote Sensing Satellite Data and Open Data," International Journal of Advanced Computer Science and Applications,, vol. 11, no. 10, pp. 56-65, 2020.
K. Arai and K. Seto, "Recursive Least Square : RLS Method- Based Time Series DataPrediction for Many Missing Data," International Journal of Advanced Computer Science and Applications, vol. 11, no. 11, pp. 66-72, 2020.
K. Arai, Y. Hideshima, Y. Iwak and R. Ito, "Method for Estimation of Oleic Acid Content in Soy Plants using Green Band Data of Sentinel-2/MSI," International Journalof Advanced Computer Science and Applications, vol. 13, no. 4, pp. 56-63, 2022.
Z. Z. Oo and S. Phyu, "Time Series Prediction Based on Facebook Prophet: A Case Study, Temperature Forecasting in Myintkyina," International Journal of Applied Mathematics Electronics and Computers, vol. 4, pp. 263-267, 2020.
A. Khurana, "Second wave of COVID-19: Steps and future vision," Indian J. Res.Homoeopath, vol. 15, pp. 75-76, 2021.
J. Hyun, Y. Lee and H. M. Son, "Synthetic Data Generation System for AI-BasedDiabetic Foot Diagnosis," Springer, vol. 2, no. 5, 2021.
D. D. Chuwang and W. Chen, "Forecasting Daily and Weekly Passenger Demand forUrban Rail Transit Stations Based on a Time Series Model Approach," MDPI, vol. 4,pp. 904-924, 2022.
