Publication Date

Fall 2023

Degree Type

Master's Project

Degree Name

Master of Science in Data Science (MSDS)


Computer Science

First Advisor

Genya Ishigaki


Time Series, Traffic Forecasting, Predictive Learning, Non-Stationarity, Spiking Neural Networks, Long Short-Term Memory.


Online web traffic forecasting is one of the most crucial elements of maintaining and improving websites and digital platforms. Traffic patterns usually predict future online traffic, including page views, unique visitors, session duration, and bounce rates. However, it is challenging to forecast non-stationary online web traffic, particularly when the data has spikes or irregular patterns. This non-stationary property demands a more advanced forecasting technique. In this study, we provide a neural networkbased method, Spiking Neural Networks (SNNs), for dealing with the data spikes and irregular patterns in non-stationary data. In our study, we compared the forecasting results of SNNs with traditional and popular time-series prediction methods like Long Short-Term Memory (LSTM) networks and Seasonal AutoRegressive Integrated Moving Average with exogenous variables (SARIMAX). The evaluation was based on prediction error metrics such as Mean Square Error (RMSE) and the Mean Absolute Error (MAE). Our results found that SNNs worked better in forecasting the non-stationary web traffic data when compared to the traditional methods. This effective forecasting technique by SNNs can be crucial in sectors like e-commerce and digital marketing, where accurately predicting the traffic helps optimize resources and improve digital strategies.

Included in

Data Science Commons