Cloud-Driven Web Traffic Forecasting with Facebook Prophet for Accurate Trend Analysis
Keywords:
Web traffic forecasting, Facebook Prophet, Cloud-driven solutions, Trend analysis, Predictive accuracyAbstract
Facebook Prophet uses machine learning and cloud architecture to anticipate online traffic patterns and analyze trends. Businesses and platforms with high user involvement may improve decision-making by precisely anticipating traffic variations and improving resource allocation. Time series data with seasonal components is used to examine previous online traffic and anticipate future patterns using Facebook Prophet. The purpose is to optimize operational tactics, predict traffic spikes, and better allocate resources. This solution uses Prophet's powerful forecasting and cloud computing's scalability and flexibility to make real-time modifications based on predicted findings. Cloud-based technologies improve forecasting accuracy and online traffic management, improving web-based operations performance and scalability. Five days of Web_Traffic_Metrics data with five parameters were selected for research. The page views range from 2550 to 8082, the unique visitors from 1211 to 4118, the bounce rate from 34.09 to 48.38, and the session duration from 151.38 to 295.38, and the peak hour from 10 am to 5 pm. From Forecast_Accuracy Five datasets with five parameters were sampled. RMSE ranges from 12.32 to 63.04, MAPE from 2.87 to 8.45, MAE from 12.16 to 46.41, R² Score from 0.85 to 0.952, and Training Time (s) from 23.09 to 55.49. Five weeks of Anomaly_Trends data with four parameters were examined. Morning, afternoon, evening, night.
References
[1]. M. Elseidi, “A Hybrid Facebook Prophet-ARIMA Framework for Forecasting High-Frequency Temperature Data,” Modeling Earth Systems and Environment, vol. 10, no. 2, pp. 1855-1867, 2024.
[2]. S. Ghimire, R. C. Deo, S. A. Pourmousavi, D. Casillas-Pérez, and S. Salcedo-Sanz, “Point-Based and Probabilistic Electricity Demand Prediction with a Neural Facebook Prophet and Kernel Density Estimation Model,” Engineering Applications of Artificial Intelligence, vol. 135, pp. 1-28, 2024.
[3]. E. Annapoorna, S. V. Sujil, S. S, S. Abhishek, and A. T, “Revolutionizing Stock Price Prediction with Automated Facebook Prophet Analysis,” International Conference on Inventive Computation Technologies, pp. 1307-1314, 2024.
[4]. S. R. Thumala, V. Mane, T. Patil, P. Tambe and C. Inamdar, "Full Stack Video Conferencing App using TypeScript and NextJS," 3rd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS), pp. 1285-1291, 2025.
[5]. A. Noertjahyana, S. A. Ananda, and D. K. Yabes, “A Comparative Study Between the Facebook Prophet Model and SARIMA for Bitcoin Price Prediction,” IJIRSET, vol. 13, no. 1, pp. 9-15, 2024.
[6]. V. Ramesh, “Evaluating Apache Kafka performance and operational efficiency: A comparative study of ZooKeeper and KRaft architectures,” International Journal of Computer Applications, vol. 187, no. 46, pp. 12–18, 2025.
[7]. A. du Toit, S. Baadel, and S. Harguem, “Predicting Tesla: Stock Market Forecasting Using Facebook's Prophet,” IEEE International Conference on Artificial Intelligence and Mechatronics Systems, pp. 1-6, Bandung, Indonesia, 2024.
[8]. A. Bekkar, B. Hssina, S. Douzi, and K. Douzi, “Forecasting Ozone Levels in Morocco: A Comparative Study of SARIMA and FB Prophet Models,” in Advancements in Climate and Smart Environment Technology, pp. 9-28, 2024.
[9]. N. Ganesh, A. Sriram, S. N. Krishnan, and T. S. Rao, “Simultaneous enhancement and detection of brain tumors using GAN,” in Intelligent Computing—Proceedings of the Computing Conference, pp. 206–220, 2025.
[10]. R. R. Vanam, V. V. Yadavali, S. Elumalai and S. R, "Software Vulnerability Detection in Source Code Using Superb Fairy-Wren Deep Transformer Guided Model for Next Generation Software Security," 6th International Conference on Inventive Research in Computing Applications , pp. 101-106, 2025.
[11]. H. Hery, C. A. Haryani, A. E. Widjaja, and A. R. Mitra, “Harnessing the Power of Prophet Algorithm for Advanced Predictive Modeling of Grab Holdings Stock Prices,” Journal of Applied Data Sciences, vol. 5, no. 2, pp. 326-341, 2024.
[12]. R. Narwal, and H. Aggarwal, “ARIMA, Prophet, and LSTM-Based Analysis of Demographic Factors in Smartphone Usage Patterns,” Microsystem Technologies, pp. 1-14, 2024.
[13]. Z. Xiong, E. Farazdaghi, J. Jeong, N. Guillou, and G. Chapalain, “Sea Surface Salinity Forecasting with a Comparison Studying Case of GMM-VSG and FB-Prophet Model,” Journal of Civil Engineering and Construction, vol. 13, no. 1, pp. 12-28, 2024.
[14]. S. R. Thumala, “Importance of business continuity and disaster recovery (BCDR) methodologies for organizations: A comparison study between AWS and Azure,” International Journal of Science and Research (IJSR), vol. 11, no. 12, pp. 1406–1415, 2022.
[15]. P. Anand, M. Sharma, and A. Saroliya, “A Comparative Analysis of Artificial Neural Networks in Time Series Forecasting Using ARIMA vs Prophet,” International Conference on Communication, Computer Sciences and Engineering, pp. 527-533, 2024.
[16]. V. Ramesh, “Performance benefits of reactive frameworks,” International Journal of Computer Applications, vol. 975, pp. 8887, 2025.
[17]. M. I. Jabed, “Stock Market Price Prediction Using Machine Learning Techniques,” American International Journal of Sciences and Engineering Research, vol. 7, no. 1, pp. 1-6, 2024.
[18]. H. Madathala, S. R. Thumala, B. Barmavat, and K. K. S. Prakash, “Functional consideration in cloud migration,” International Peer Reviewed/Refereed Multidisciplinary Journal (EIPRMJ), vol. 13, no. 2, 2024.
[19]. A. C. Wijaya, Sutikno, Khadijah, R. Kusumaningrum, A. Sugiharto, and G. Aryotejo, “Prophet Algorithm Optimization with Particle Swarm Optimization for Adjusted Closing Price Forecasting in Xiaomi Corporation,” 7th International Conference on Informatics and Computational Sciences, pp. 376-381, 2024.
[20]. A. L. Serrano, G. A. Rodrigues, P. H. Martins, G. M. Saiki, G. P. Filho, V. P. Gonçalves, and R. D. Albuquerque, “Statistical Comparison of Time Series Models for Forecasting Brazilian Monthly Energy Demand Using Economic, Industrial, and Climatic Exogenous Variables,” Applied Sciences, vol. 14, no. 13, pp. 1-32, 2024
