Hybrid Models for Vegetable Price Forecasting With Online Searching Information

Abstract

Purpose: This study aims to propose a hybrid model that integrates machine learning techniques with time series modeling and takes into account the Internet information represented by Google Trends to combine structural data and big data for vegetable price modeling. The hybrid model is expected to enhance the prediction performance of vegetable prices. Design/methodology/approach: Time series models commonly used for price prediction (e.g., autoregressive integrated moving average model [ARIMA], autoregressive conditional heteroscedasticity model [ARCH], and generalized ARCH model [GARCH]) and machine learning techniques usually used for vegetable price forecast (e.g., artificial neural networks [ANN] and support vector regression [SVR]) are selected to obtain prediction models in this study. Seven prediction models classified into three categories are selected for empirical comparison: (1) time series model, ANN, and SVR models fitted with only cabbage prices, (2) ANN and SVR models fitted with both cabbage prices and Google Trends, and (3) two hybrid models, integrated time series model with machine learning techniques (SVR or ANN) and fitted with both cabbage prices and Google Trends. Daily cabbage prices and its Google Trends of searching volumes are used for empirical analysis. The prediction performance of seven prediction models is compared based on the mean absolute percentage error (MAPE), mean absolute error (MAE), and the root mean squared error (RMSE). Findings: Study results show that (1) the models considering the information of Google Trends with cabbage prices perform better than those models using only cabbage prices, (2) the hybrid models presented in this paper have significantly improved the prediction performance of the time series model, and (3) the hybrid model integrated time series model with SVR algorithm has the best prediction performance. Practical implications: In practice, the hybrid model proposed in this study can be applied to vegetable price forecasting to improve prediction performance. Originality/value: Our study findings contribute to the forecasting methodology of integrated statistical modeling with machine learning techniques and using both structural data and big data for improving prediction modeling of vegetable prices.