The aim of this research work was applying a suitable forecasting technique to predict web site visits. Thus, the results derived through forecasting will be assist web site owners in,
- Predict total number of visitors within next WEEK time.
- Predict number of visitors on a given DAY (Sunday, Monday, etc) within next WEEK time.
In this research four of classifier functions are used. They are namely Gaussian Process, Multilayer Perceptron, Linear Regression and SMO Regression.Based on the evaluation results i finally conclude that SMO regression and Linear Regression algorithms are better suited for forecasting web site related information and also using Linear Regression on pre-processed data gives more accurate results.
Added on 16/12/2013:
Paper was published in this journal
Full Paper: Web Site Visit Forecasting Using Data Mining Techniques
C. Napagoda, “Web Site Visit Forecasting Using Data Mining Techniques,” International Journal of Scientific & Technology Research, vol. VOLUME 2, no. ISSUE 12, pp. 170–174.