Title: A comparative analysis of forecast models with online search volume: An application of price forecast on vegetables
Authors: Yi-Wen Yeh - National Taipei University (Taiwan) [presenting]
Abstract: Along with the popularity of internet, people start to look for information by Internet. Search volumes gradually become the factor to affect vegetable prices. We take into account the information of search volume to enhance statistical modeling. Moreover, we compare the forecasting performances among time series model, the statistical modeling usually used in economy, and various analysis techniques with machine learning including neural networks and support vector regression. Furthermore, we attempt to build up a hybrid model which integrates time series with one of neural networks and support vector regression. An empirical analysis is conducted by using daily prices of cabbage. The results suggest an appropriate model for predicting cabbage prices.